W0217 01:26:29.343000 284026 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:29.343000 284026 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:29.343000 284026 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:29.343000 284026 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:29.970000 208189 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:29.970000 208189 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:29.970000 208189 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:29.970000 208189 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.368000 3877268 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.368000 3877268 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.368000 3877268 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.368000 3877268 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.381000 2493811 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.381000 2493811 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.381000 2493811 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.381000 2493811 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.443000 2952825 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.443000 2952825 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.443000 2952825 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.443000 2952825 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.448000 1034984 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.448000 1034984 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.448000 1034984 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.448000 1034984 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.467000 69771 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.467000 69771 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.467000 69771 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.467000 69771 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.471000 810550 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.471000 810550 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.471000 810550 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.471000 810550 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.472000 3567966 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.472000 3567966 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.472000 3567966 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.472000 3567966 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.531000 1749965 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.531000 1749965 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.531000 1749965 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.531000 1749965 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.621000 4067075 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.621000 4067075 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.621000 4067075 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.621000 4067075 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.659000 624291 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.659000 624291 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.659000 624291 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.659000 624291 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.933000 671409 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.933000 671409 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.933000 671409 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.933000 671409 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.963000 2016063 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:30.963000 2016063 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:30.963000 2016063 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:30.963000 2016063 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:31.066000 3205026 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:26:31.066000 3205026 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:26:31.066000 3205026 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:26:31.066000 3205026 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
slurmstepd: error: Prolog hung on node h100-st-p548xlarge-315
W0217 01:27:14.540000 2019032 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0217 01:27:14.540000 2019032 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0217 01:27:14.540000 2019032 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0217 01:27:14.540000 2019032 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Loading checkpoint shards: 0%| | 0/5 [00:00', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.99it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 4.49it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 4.36it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.65it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.93it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.86it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:00<00:00, 4.64it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.71it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:00<00:00, 4.69it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:00<00:00, 4.58it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.08it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.59it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.53it/s]loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.85it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.54it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file added_tokens.json from cache at None
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file special_tokens_map.json from cache at None
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 4.00it/s]loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.11it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.96it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.94it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.80it/s]loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.90it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.61it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.81it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.48it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file chat_template.jinja from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Loading checkpoint shards: 0%| | 0/5 [00:00', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.75it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.11it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.98it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.08it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.93it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.99it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.80it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 4.05it/s]loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.38it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.03it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Loading checkpoint shards: 0%| | 0/5 [00:00', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
: 20%|██ | 1/5 [00:00<00:01, 3.32it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.10it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 4.42it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.72it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.62it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 4.11it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.91it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.23it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.49it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.63it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 4.68it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 4.44it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00,Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
3.85it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.81it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 4.05it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.47it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.74it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.84it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:00<00:00, 4.81it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:00<00:00, 4.64it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:00<00:00, 4.33it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 4.10it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.91it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.75it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.40it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.89it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.97it/s]loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.76it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.92it/s]loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.81it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.53it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.59it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.31it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.43it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.08it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.90it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.84it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.05it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.83it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.08it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.90it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
[rank18]: Traceback (most recent call last):
[rank18]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank18]: train(attn_implementation="flash_attention_2")
[rank18]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank18]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank18]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank18]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank18]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank18]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank18]: AttributeError: 'function' object has no attribute 'glob'
[rank84]: Traceback (most recent call last):
[rank84]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank84]: train(attn_implementation="flash_attention_2")
[rank84]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank84]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank84]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank84]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank84]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank84]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank84]: AttributeError: 'function' object has no attribute 'glob'
[rank80]: Traceback (most recent call last):
[rank80]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank80]: train(attn_implementation="flash_attention_2")
[rank80]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank80]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank80]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank80]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank80]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank80]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank80]: AttributeError: 'function' object has no attribute 'glob'
[rank45]: Traceback (most recent call last):
[rank45]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank45]: train(attn_implementation="flash_attention_2")
[rank45]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank45]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank45]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank45]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank45]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank45]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank45]: AttributeError: 'function' object has no attribute 'glob'
[rank81]: Traceback (most recent call last):
[rank81]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank81]: train(attn_implementation="flash_attention_2")
[rank81]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank81]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank81]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank81]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank81]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank81]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank81]: AttributeError: 'function' object has no attribute 'glob'
[rank36]: Traceback (most recent call last):
[rank36]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank36]: train(attn_implementation="flash_attention_2")
[rank36]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank36]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank36]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank36]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank36]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank36]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank36]: AttributeError: 'function' object has no attribute 'glob'
[rank19]: Traceback (most recent call last):
[rank19]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank19]: train(attn_implementation="flash_attention_2")
[rank19]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank19]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank19]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank19]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank19]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank19]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank19]: AttributeError: 'function' object has no attribute 'glob'
[rank50]: Traceback (most recent call last):
[rank50]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank50]: train(attn_implementation="flash_attention_2")
[rank50]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank50]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank50]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank50]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank50]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank50]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank50]: AttributeError: 'function' object has no attribute 'glob'
[rank111]: Traceback (most recent call last):
[rank111]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank111]: train(attn_implementation="flash_attention_2")
[rank111]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank111]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank111]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank111]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank111]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank111]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank111]: AttributeError: 'function' object has no attribute 'glob'
[rank16]: Traceback (most recent call last):
[rank16]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank16]: train(attn_implementation="flash_attention_2")
[rank16]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank16]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank16]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank16]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank16]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank16]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank16]: AttributeError: 'function' object has no attribute 'glob'
[rank100]: Traceback (most recent call last):
[rank100]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank100]: train(attn_implementation="flash_attention_2")
[rank100]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank100]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank100]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank100]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank100]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank100]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank100]: AttributeError: 'function' object has no attribute 'glob'
[rank65]: Traceback (most recent call last):
[rank65]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank65]: train(attn_implementation="flash_attention_2")
[rank65]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank65]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank65]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank65]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank65]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank65]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank65]: AttributeError: 'function' object has no attribute 'glob'
[rank93]: Traceback (most recent call last):
[rank93]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank93]: train(attn_implementation="flash_attention_2")
[rank93]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank93]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank93]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank93]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank93]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank93]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank93]: AttributeError: 'function' object has no attribute 'glob'
[rank9]: Traceback (most recent call last):
[rank9]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank9]: train(attn_implementation="flash_attention_2")
[rank9]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank9]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank9]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank9]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank9]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank9]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank9]: AttributeError: 'function' object has no attribute 'glob'
[rank122]: Traceback (most recent call last):
[rank122]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank122]: train(attn_implementation="flash_attention_2")
[rank122]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank122]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank122]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank122]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank122]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank122]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank122]: AttributeError: 'function' object has no attribute 'glob'
[rank43]: Traceback (most recent call last):
[rank43]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank43]: train(attn_implementation="flash_attention_2")
[rank43]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank43]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank43]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank43]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank43]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank43]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank43]: AttributeError: 'function' object has no attribute 'glob'
[rank26]: Traceback (most recent call last):
[rank26]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank26]: train(attn_implementation="flash_attention_2")
[rank26]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank26]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank26]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank26]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank26]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank26]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank26]: AttributeError: 'function' object has no attribute 'glob'
[rank126]: Traceback (most recent call last):
[rank126]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank126]: train(attn_implementation="flash_attention_2")
[rank126]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank126]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank126]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank126]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank126]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank126]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank126]: AttributeError: 'function' object has no attribute 'glob'
[rank37]: Traceback (most recent call last):
[rank37]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank37]: train(attn_implementation="flash_attention_2")
[rank37]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank37]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank37]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank37]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank37]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank37]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank37]: AttributeError: 'function' object has no attribute 'glob'
[rank115]: Traceback (most recent call last):
[rank115]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank115]: train(attn_implementation="flash_attention_2")
[rank115]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank115]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank115]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank115]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank115]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank115]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank115]: AttributeError: 'function' object has no attribute 'glob'
[rank118]: Traceback (most recent call last):
[rank118]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank118]: train(attn_implementation="flash_attention_2")
[rank118]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank118]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank118]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank118]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank118]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank118]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank118]: AttributeError: 'function' object has no attribute 'glob'
[rank38]: Traceback (most recent call last):
[rank38]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank38]: train(attn_implementation="flash_attention_2")
[rank38]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank38]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank38]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank38]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank38]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank38]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank38]: AttributeError: 'function' object has no attribute 'glob'
[rank82]: Traceback (most recent call last):
[rank82]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank82]: train(attn_implementation="flash_attention_2")
[rank82]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank82]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank82]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank82]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank82]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank82]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank82]: AttributeError: 'function' object has no attribute 'glob'
[rank4]: Traceback (most recent call last):
[rank4]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank4]: train(attn_implementation="flash_attention_2")
[rank4]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank4]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank4]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank4]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank4]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank4]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank4]: AttributeError: 'function' object has no attribute 'glob'
[rank91]: Traceback (most recent call last):
[rank91]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank91]: train(attn_implementation="flash_attention_2")
[rank91]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank91]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank91]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank91]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank91]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank91]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank91]: AttributeError: 'function' object has no attribute 'glob'
[rank5]: Traceback (most recent call last):
[rank5]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank5]: train(attn_implementation="flash_attention_2")
[rank5]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank5]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank5]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank5]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank5]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank5]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank5]: AttributeError: 'function' object has no attribute 'glob'
[rank80]:[W217 01:32:03.613980202 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
[rank35]: Traceback (most recent call last):
[rank35]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank35]: train(attn_implementation="flash_attention_2")
[rank35]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank35]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank35]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank35]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank35]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank35]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank35]: AttributeError: 'function' object has no attribute 'glob'
[rank29]: Traceback (most recent call last):
[rank29]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank29]: train(attn_implementation="flash_attention_2")
[rank29]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank29]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank29]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank29]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank29]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank29]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank29]: AttributeError: 'function' object has no attribute 'glob'
[rank33]: Traceback (most recent call last):
[rank33]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank33]: train(attn_implementation="flash_attention_2")
[rank33]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank33]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank33]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank33]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank33]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank33]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank33]: AttributeError: 'function' object has no attribute 'glob'
[rank99]: Traceback (most recent call last):
[rank99]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank99]: train(attn_implementation="flash_attention_2")
[rank99]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank99]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank99]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank99]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank99]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank99]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank99]: AttributeError: 'function' object has no attribute 'glob'
[rank105]: Traceback (most recent call last):
[rank105]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank105]: train(attn_implementation="flash_attention_2")
[rank105]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank105]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank105]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank105]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank105]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank105]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank105]: AttributeError: 'function' object has no attribute 'glob'
[rank97]: Traceback (most recent call last):
[rank97]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank97]: train(attn_implementation="flash_attention_2")
[rank97]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank97]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank97]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank97]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank97]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank97]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank97]: AttributeError: 'function' object has no attribute 'glob'
[rank113]: Traceback (most recent call last):
[rank113]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank113]: train(attn_implementation="flash_attention_2")
[rank113]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank113]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank113]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank113]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank113]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank113]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank113]: AttributeError: 'function' object has no attribute 'glob'
[rank55]: Traceback (most recent call last):
[rank55]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank55]: train(attn_implementation="flash_attention_2")
[rank55]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank55]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank55]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank55]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank55]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank55]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank55]: AttributeError: 'function' object has no attribute 'glob'
[rank85]: Traceback (most recent call last):
[rank85]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank85]: train(attn_implementation="flash_attention_2")
[rank85]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank85]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank85]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank85]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank85]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank85]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank85]: AttributeError: 'function' object has no attribute 'glob'
[rank86]: Traceback (most recent call last):
[rank86]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank86]: train(attn_implementation="flash_attention_2")
[rank86]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank86]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank86]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank86]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank86]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank86]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank86]: AttributeError: 'function' object has no attribute 'glob'
[rank24]: Traceback (most recent call last):
[rank24]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank24]: train(attn_implementation="flash_attention_2")
[rank24]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank24]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank24]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank24]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank24]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank24]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank24]: AttributeError: 'function' object has no attribute 'glob'
[rank119]: Traceback (most recent call last):
[rank119]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank119]: train(attn_implementation="flash_attention_2")
[rank119]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank119]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank119]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank119]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank119]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank119]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank119]: AttributeError: 'function' object has no attribute 'glob'
[rank6]: Traceback (most recent call last):
[rank6]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank6]: train(attn_implementation="flash_attention_2")
[rank6]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank6]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank6]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank6]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank6]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank6]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank6]: AttributeError: 'function' object has no attribute 'glob'
[rank31]: Traceback (most recent call last):
[rank31]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank31]: train(attn_implementation="flash_attention_2")
[rank31]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank31]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank31]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank31]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank31]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank31]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank31]: AttributeError: 'function' object has no attribute 'glob'
[rank46]: Traceback (most recent call last):
[rank46]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank46]: train(attn_implementation="flash_attention_2")
[rank46]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank46]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank46]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank46]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank46]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank46]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank46]: AttributeError: 'function' object has no attribute 'glob'
[rank98]: Traceback (most recent call last):
[rank98]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank98]: train(attn_implementation="flash_attention_2")
[rank98]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank98]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank98]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank98]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank98]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank98]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank98]: AttributeError: 'function' object has no attribute 'glob'
[rank44]: Traceback (most recent call last):
[rank44]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank44]: train(attn_implementation="flash_attention_2")
[rank44]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank44]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank44]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank44]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank44]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank44]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank44]: AttributeError: 'function' object has no attribute 'glob'
[rank0]: Traceback (most recent call last):
[rank0]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank0]: train(attn_implementation="flash_attention_2")
[rank0]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank0]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank0]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank0]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank0]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank0]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank0]: AttributeError: 'function' object has no attribute 'glob'
[rank124]: Traceback (most recent call last):
[rank124]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank124]: train(attn_implementation="flash_attention_2")
[rank124]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank124]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank124]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank124]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank124]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank124]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank124]: AttributeError: 'function' object has no attribute 'glob'
[rank28]: Traceback (most recent call last):
[rank28]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank28]: train(attn_implementation="flash_attention_2")
[rank28]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank28]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank28]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank28]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank28]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank28]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank28]: AttributeError: 'function' object has no attribute 'glob'
[rank127]: Traceback (most recent call last):
[rank127]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank127]: train(attn_implementation="flash_attention_2")
[rank127]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank127]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank127]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank127]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank127]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank127]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank127]: AttributeError: 'function' object has no attribute 'glob'
[rank117]: Traceback (most recent call last):
[rank117]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank117]: train(attn_implementation="flash_attention_2")
[rank117]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank117]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank117]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank117]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank117]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank117]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank117]: AttributeError: 'function' object has no attribute 'glob'
[rank41]: Traceback (most recent call last):
[rank41]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank41]: train(attn_implementation="flash_attention_2")
[rank41]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank41]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank41]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank41]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank41]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank41]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank41]: AttributeError: 'function' object has no attribute 'glob'
[rank106]: Traceback (most recent call last):
[rank106]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank106]: train(attn_implementation="flash_attention_2")
[rank106]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank106]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank106]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank106]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank106]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank106]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank106]: AttributeError: 'function' object has no attribute 'glob'
[rank70]: Traceback (most recent call last):
[rank70]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank70]: train(attn_implementation="flash_attention_2")
[rank70]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank70]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank70]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank70]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank70]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank70]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank70]: AttributeError: 'function' object has no attribute 'glob'
[rank42]: Traceback (most recent call last):
[rank42]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank42]: train(attn_implementation="flash_attention_2")
[rank42]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank42]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank42]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank42]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank42]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank42]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank42]: AttributeError: 'function' object has no attribute 'glob'
[rank12]: Traceback (most recent call last):
[rank12]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank12]: train(attn_implementation="flash_attention_2")
[rank12]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank12]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank12]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank12]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank12]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank12]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank12]: AttributeError: 'function' object has no attribute 'glob'
[rank103]: Traceback (most recent call last):
[rank103]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank103]: train(attn_implementation="flash_attention_2")
[rank103]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank103]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank103]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank103]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank103]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank103]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank103]: AttributeError: 'function' object has no attribute 'glob'
[rank21]: Traceback (most recent call last):
[rank21]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank21]: train(attn_implementation="flash_attention_2")
[rank21]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank21]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank21]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank21]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank21]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank21]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank21]: AttributeError: 'function' object has no attribute 'glob'
[rank51]: Traceback (most recent call last):
[rank51]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank51]: train(attn_implementation="flash_attention_2")
[rank51]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank51]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank51]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank51]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank51]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank51]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank51]: AttributeError: 'function' object has no attribute 'glob'
[rank10]: Traceback (most recent call last):
[rank10]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank10]: train(attn_implementation="flash_attention_2")
[rank10]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank10]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank10]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank10]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank10]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank10]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank10]: AttributeError: 'function' object has no attribute 'glob'
[rank54]: Traceback (most recent call last):
[rank54]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank54]: train(attn_implementation="flash_attention_2")
[rank54]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank54]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank54]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank54]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank54]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank54]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank54]: AttributeError: 'function' object has no attribute 'glob'
[rank25]: Traceback (most recent call last):
[rank25]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank25]: train(attn_implementation="flash_attention_2")
[rank25]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank25]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank25]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank25]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank25]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank25]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank25]: AttributeError: 'function' object has no attribute 'glob'
[rank22]: Traceback (most recent call last):
[rank22]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank22]: train(attn_implementation="flash_attention_2")
[rank22]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank22]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank22]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank22]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank22]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank22]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank22]: AttributeError: 'function' object has no attribute 'glob'
[rank3]: Traceback (most recent call last):
[rank3]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank3]: train(attn_implementation="flash_attention_2")
[rank3]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank3]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank3]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank3]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank3]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank3]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank3]: AttributeError: 'function' object has no attribute 'glob'
[rank7]: Traceback (most recent call last):
[rank7]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank7]: train(attn_implementation="flash_attention_2")
[rank7]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank7]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank7]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank7]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank7]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank7]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank7]: AttributeError: 'function' object has no attribute 'glob'
[rank17]: Traceback (most recent call last):
[rank17]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank17]: train(attn_implementation="flash_attention_2")
[rank17]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank17]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank17]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank17]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank17]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank17]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank17]: AttributeError: 'function' object has no attribute 'glob'
[rank30]: Traceback (most recent call last):
[rank30]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank30]: train(attn_implementation="flash_attention_2")
[rank30]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank30]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank30]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank30]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank30]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank30]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank30]: AttributeError: 'function' object has no attribute 'glob'
[rank87]: Traceback (most recent call last):
[rank87]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank87]: train(attn_implementation="flash_attention_2")
[rank87]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank87]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank87]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank87]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank87]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank87]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank87]: AttributeError: 'function' object has no attribute 'glob'
[rank120]: Traceback (most recent call last):
[rank120]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank120]: train(attn_implementation="flash_attention_2")
[rank120]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank120]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank120]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank120]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank120]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank120]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank120]: AttributeError: 'function' object has no attribute 'glob'
[rank101]: Traceback (most recent call last):
[rank101]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank101]: train(attn_implementation="flash_attention_2")
[rank101]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank101]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank101]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank101]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank101]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank101]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank101]: AttributeError: 'function' object has no attribute 'glob'
[rank48]: Traceback (most recent call last):
[rank48]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank48]: train(attn_implementation="flash_attention_2")
[rank48]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank48]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank48]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank48]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank48]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank48]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank48]: AttributeError: 'function' object has no attribute 'glob'
[rank1]: Traceback (most recent call last):
[rank1]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank1]: train(attn_implementation="flash_attention_2")
[rank1]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank1]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank1]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank1]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank1]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank1]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank1]: AttributeError: 'function' object has no attribute 'glob'
[rank20]: Traceback (most recent call last):
[rank20]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank20]: train(attn_implementation="flash_attention_2")
[rank20]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank20]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank20]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank20]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank20]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank20]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank20]: AttributeError: 'function' object has no attribute 'glob'
[rank107]: Traceback (most recent call last):
[rank107]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank107]: train(attn_implementation="flash_attention_2")
[rank107]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank107]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank107]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank107]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank107]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank107]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank107]: AttributeError: 'function' object has no attribute 'glob'
[rank49]: Traceback (most recent call last):
[rank49]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank49]: train(attn_implementation="flash_attention_2")
[rank49]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank49]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank49]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank49]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank49]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank49]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank49]: AttributeError: 'function' object has no attribute 'glob'
[rank83]: Traceback (most recent call last):
[rank83]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank83]: train(attn_implementation="flash_attention_2")
[rank83]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank83]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank83]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank83]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank83]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank83]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank83]: AttributeError: 'function' object has no attribute 'glob'
[rank109]: Traceback (most recent call last):
[rank109]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank109]: train(attn_implementation="flash_attention_2")
[rank109]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank109]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank109]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank109]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank109]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank109]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank109]: AttributeError: 'function' object has no attribute 'glob'
[rank2]: Traceback (most recent call last):
[rank2]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank2]: train(attn_implementation="flash_attention_2")
[rank2]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank2]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank2]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank2]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank2]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank2]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank2]: AttributeError: 'function' object has no attribute 'glob'
[rank121]: Traceback (most recent call last):
[rank121]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank121]: train(attn_implementation="flash_attention_2")
[rank121]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank121]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank121]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank121]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank121]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank121]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank121]: AttributeError: 'function' object has no attribute 'glob'
[rank64]: Traceback (most recent call last):
[rank64]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank64]: train(attn_implementation="flash_attention_2")
[rank64]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank64]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank64]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank64]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank64]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank64]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank64]: AttributeError: 'function' object has no attribute 'glob'
[rank27]: Traceback (most recent call last):
[rank27]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank27]: train(attn_implementation="flash_attention_2")
[rank27]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank27]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank27]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank27]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank27]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank27]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank27]: AttributeError: 'function' object has no attribute 'glob'
[rank40]: Traceback (most recent call last):
[rank40]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank40]: train(attn_implementation="flash_attention_2")
[rank40]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank40]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank40]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank40]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank40]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank40]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank40]: AttributeError: 'function' object has no attribute 'glob'
[rank15]: Traceback (most recent call last):
[rank15]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank15]: train(attn_implementation="flash_attention_2")
[rank15]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank15]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank15]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank15]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank15]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank15]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank15]: AttributeError: 'function' object has no attribute 'glob'
[rank23]: Traceback (most recent call last):
[rank23]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank23]: train(attn_implementation="flash_attention_2")
[rank23]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank23]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank23]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank23]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank23]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank23]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank23]: AttributeError: 'function' object has no attribute 'glob'
[rank92]: Traceback (most recent call last):
[rank92]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank92]: train(attn_implementation="flash_attention_2")
[rank92]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank92]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank92]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank92]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank92]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank92]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank92]: AttributeError: 'function' object has no attribute 'glob'
[rank125]: Traceback (most recent call last):
[rank125]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank125]: train(attn_implementation="flash_attention_2")
[rank125]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank125]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank125]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank125]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank125]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank125]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank125]: AttributeError: 'function' object has no attribute 'glob'
[rank47]: Traceback (most recent call last):
[rank47]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank47]: train(attn_implementation="flash_attention_2")
[rank47]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank47]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank47]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank47]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank47]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank47]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank47]: AttributeError: 'function' object has no attribute 'glob'
[rank39]: Traceback (most recent call last):
[rank39]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank39]: train(attn_implementation="flash_attention_2")
[rank39]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank39]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank39]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank39]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank39]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank39]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank39]: AttributeError: 'function' object has no attribute 'glob'
[rank123]: Traceback (most recent call last):
[rank123]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank123]: train(attn_implementation="flash_attention_2")
[rank123]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank123]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank123]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank123]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank123]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank123]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank123]: AttributeError: 'function' object has no attribute 'glob'
[rank63]: Traceback (most recent call last):
[rank63]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank63]: train(attn_implementation="flash_attention_2")
[rank63]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank63]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank63]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank63]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank63]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank63]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank63]: AttributeError: 'function' object has no attribute 'glob'
[rank52]: Traceback (most recent call last):
[rank52]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank52]: train(attn_implementation="flash_attention_2")
[rank52]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank52]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank52]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank52]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank52]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank52]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank52]: AttributeError: 'function' object has no attribute 'glob'
[rank110]: Traceback (most recent call last):
[rank110]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank110]: train(attn_implementation="flash_attention_2")
[rank110]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank110]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank110]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank110]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank110]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank110]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank110]: AttributeError: 'function' object has no attribute 'glob'
[rank66]: Traceback (most recent call last):
[rank66]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank66]: train(attn_implementation="flash_attention_2")
[rank66]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank66]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank66]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank66]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank66]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank66]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank66]: AttributeError: 'function' object has no attribute 'glob'
[rank16]:[W217 01:32:04.659588692 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
[rank69]: Traceback (most recent call last):
[rank69]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank69]: train(attn_implementation="flash_attention_2")
[rank69]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank69]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank69]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank69]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank69]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank69]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank69]: AttributeError: 'function' object has no attribute 'glob'
[rank14]: Traceback (most recent call last):
[rank14]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank14]: train(attn_implementation="flash_attention_2")
[rank14]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank14]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank14]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank14]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank14]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank14]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank14]: AttributeError: 'function' object has no attribute 'glob'
[rank53]: Traceback (most recent call last):
[rank53]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank53]: train(attn_implementation="flash_attention_2")
[rank53]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank53]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank53]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank53]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank53]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank53]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank53]: AttributeError: 'function' object has no attribute 'glob'
[rank96]: Traceback (most recent call last):
[rank96]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank96]: train(attn_implementation="flash_attention_2")
[rank96]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank96]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank96]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank96]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank96]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank96]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank96]: AttributeError: 'function' object has no attribute 'glob'
[rank67]: Traceback (most recent call last):
[rank67]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank67]: train(attn_implementation="flash_attention_2")
[rank67]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank67]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank67]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank67]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank67]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank67]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank67]: AttributeError: 'function' object has no attribute 'glob'
[rank114]: Traceback (most recent call last):
[rank114]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank114]: train(attn_implementation="flash_attention_2")
[rank114]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank114]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank114]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank114]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank114]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank114]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank114]: AttributeError: 'function' object has no attribute 'glob'
[rank102]: Traceback (most recent call last):
[rank102]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank102]: train(attn_implementation="flash_attention_2")
[rank102]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank102]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank102]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank102]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank102]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank102]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank102]: AttributeError: 'function' object has no attribute 'glob'
[rank68]: Traceback (most recent call last):
[rank68]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank68]: train(attn_implementation="flash_attention_2")
[rank68]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank68]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank68]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank68]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank68]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank68]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank68]: AttributeError: 'function' object has no attribute 'glob'
[rank108]: Traceback (most recent call last):
[rank108]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank108]: train(attn_implementation="flash_attention_2")
[rank108]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank108]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank108]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank108]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank108]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank108]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank108]: AttributeError: 'function' object has no attribute 'glob'
[rank89]: Traceback (most recent call last):
[rank89]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank89]: train(attn_implementation="flash_attention_2")
[rank89]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank89]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank89]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank89]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank89]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank89]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank89]: AttributeError: 'function' object has no attribute 'glob'
[rank94]: Traceback (most recent call last):
[rank94]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank94]: train(attn_implementation="flash_attention_2")
[rank94]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank94]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank94]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank94]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank94]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank94]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank94]: AttributeError: 'function' object has no attribute 'glob'
[rank8]: Traceback (most recent call last):
[rank8]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank8]: train(attn_implementation="flash_attention_2")
[rank8]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank8]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank8]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank8]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank8]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank8]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank8]: AttributeError: 'function' object has no attribute 'glob'
[rank13]: Traceback (most recent call last):
[rank13]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank13]: train(attn_implementation="flash_attention_2")
[rank13]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank13]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank13]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank13]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank13]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank13]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank13]: AttributeError: 'function' object has no attribute 'glob'
[rank34]: Traceback (most recent call last):
[rank34]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank34]: train(attn_implementation="flash_attention_2")
[rank34]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank34]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank34]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank34]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank34]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank34]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank34]: AttributeError: 'function' object has no attribute 'glob'
[rank90]: Traceback (most recent call last):
[rank90]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank90]: train(attn_implementation="flash_attention_2")
[rank90]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank90]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank90]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank90]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank90]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank90]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank90]: AttributeError: 'function' object has no attribute 'glob'
[rank11]: Traceback (most recent call last):
[rank11]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank11]: train(attn_implementation="flash_attention_2")
[rank11]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank11]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank11]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank11]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank11]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank11]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank11]: AttributeError: 'function' object has no attribute 'glob'
[rank71]: Traceback (most recent call last):
[rank71]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank71]: train(attn_implementation="flash_attention_2")
[rank71]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank71]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank71]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank71]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank71]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank71]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank71]: AttributeError: 'function' object has no attribute 'glob'
[rank104]: Traceback (most recent call last):
[rank104]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank104]: train(attn_implementation="flash_attention_2")
[rank104]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank104]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank104]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank104]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank104]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank104]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank104]: AttributeError: 'function' object has no attribute 'glob'
[rank116]: Traceback (most recent call last):
[rank116]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank116]: train(attn_implementation="flash_attention_2")
[rank116]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank116]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank116]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank116]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank116]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank116]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank116]: AttributeError: 'function' object has no attribute 'glob'
[rank88]: Traceback (most recent call last):
[rank88]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank88]: train(attn_implementation="flash_attention_2")
[rank88]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank88]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank88]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank88]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank88]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank88]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank88]: AttributeError: 'function' object has no attribute 'glob'
[rank32]: Traceback (most recent call last):
[rank32]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank32]: train(attn_implementation="flash_attention_2")
[rank32]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank32]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank32]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank32]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank32]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank32]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank32]: AttributeError: 'function' object has no attribute 'glob'
[rank112]: Traceback (most recent call last):
[rank112]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank112]: train(attn_implementation="flash_attention_2")
[rank112]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank112]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank112]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank112]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank112]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank112]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank112]: AttributeError: 'function' object has no attribute 'glob'
[rank73]: Traceback (most recent call last):
[rank73]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank73]: train(attn_implementation="flash_attention_2")
[rank73]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank73]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank73]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank73]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank73]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank73]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank73]: AttributeError: 'function' object has no attribute 'glob'
[rank74]: Traceback (most recent call last):
[rank74]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank74]: train(attn_implementation="flash_attention_2")
[rank74]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank74]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank74]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank74]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank74]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank74]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank74]: AttributeError: 'function' object has no attribute 'glob'
[rank95]: Traceback (most recent call last):
[rank95]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank95]: train(attn_implementation="flash_attention_2")
[rank95]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank95]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank95]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank95]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank95]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank95]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank95]: AttributeError: 'function' object has no attribute 'glob'
[rank78]: Traceback (most recent call last):
[rank78]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank78]: train(attn_implementation="flash_attention_2")
[rank78]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank78]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank78]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank78]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank78]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank78]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank78]: AttributeError: 'function' object has no attribute 'glob'
[rank75]: Traceback (most recent call last):
[rank75]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank75]: train(attn_implementation="flash_attention_2")
[rank75]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank75]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank75]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank75]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank75]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank75]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank75]: AttributeError: 'function' object has no attribute 'glob'
[rank77]: Traceback (most recent call last):
[rank77]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank77]: train(attn_implementation="flash_attention_2")
[rank77]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank77]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank77]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank77]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank77]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank77]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank77]: AttributeError: 'function' object has no attribute 'glob'
[rank60]: Traceback (most recent call last):
[rank60]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank60]: train(attn_implementation="flash_attention_2")
[rank60]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank60]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank60]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank60]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank60]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank60]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank60]: AttributeError: 'function' object has no attribute 'glob'
[rank24]:[W217 01:32:04.814960404 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
[rank57]: Traceback (most recent call last):
[rank57]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank57]: train(attn_implementation="flash_attention_2")
[rank57]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank57]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank57]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank57]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank57]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank57]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank57]: AttributeError: 'function' object has no attribute 'glob'
[rank59]: Traceback (most recent call last):
[rank59]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank59]: train(attn_implementation="flash_attention_2")
[rank59]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank59]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank59]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank59]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank59]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank59]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank59]: AttributeError: 'function' object has no attribute 'glob'
W0217 01:32:05.083000 208189 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 209046 closing signal SIGTERM
W0217 01:32:05.084000 208189 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 209047 closing signal SIGTERM
W0217 01:32:05.084000 208189 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 209049 closing signal SIGTERM
W0217 01:32:05.085000 208189 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 209050 closing signal SIGTERM
W0217 01:32:05.085000 208189 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 209051 closing signal SIGTERM
W0217 01:32:05.085000 208189 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 209052 closing signal SIGTERM
W0217 01:32:05.086000 208189 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 209053 closing signal SIGTERM
[rank79]: Traceback (most recent call last):
[rank79]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank79]: train(attn_implementation="flash_attention_2")
[rank79]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank79]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank79]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank79]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank79]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank79]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank79]: AttributeError: 'function' object has no attribute 'glob'
[rank0]:[W217 01:32:05.486806216 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
[rank76]: Traceback (most recent call last):
[rank76]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank76]: train(attn_implementation="flash_attention_2")
[rank76]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank76]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank76]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank76]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank76]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank76]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank76]: AttributeError: 'function' object has no attribute 'glob'
[rank120]:[W217 01:32:05.642331198 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
[rank61]: Traceback (most recent call last):
[rank61]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank61]: train(attn_implementation="flash_attention_2")
[rank61]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank61]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank61]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank61]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank61]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank61]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank61]: AttributeError: 'function' object has no attribute 'glob'
[rank48]:[W217 01:32:05.562100144 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
[rank62]: Traceback (most recent call last):
[rank62]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank62]: train(attn_implementation="flash_attention_2")
[rank62]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank62]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank62]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank62]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank62]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank62]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank62]: AttributeError: 'function' object has no attribute 'glob'
[rank96]:[W217 01:32:05.214926312 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
[rank58]: Traceback (most recent call last):
[rank58]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank58]: train(attn_implementation="flash_attention_2")
[rank58]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank58]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank58]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank58]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank58]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank58]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank58]: AttributeError: 'function' object has no attribute 'glob'
[rank72]: Traceback (most recent call last):
[rank72]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank72]: train(attn_implementation="flash_attention_2")
[rank72]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank72]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank72]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank72]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank72]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank72]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank72]: AttributeError: 'function' object has no attribute 'glob'
[rank64]:[W217 01:32:05.056373451 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
[rank40]:[W217 01:32:05.161810329 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
W0217 01:32:05.664000 671409 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 673296 closing signal SIGTERM
W0217 01:32:05.665000 671409 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 673297 closing signal SIGTERM
W0217 01:32:05.665000 671409 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 673298 closing signal SIGTERM
W0217 01:32:05.666000 671409 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 673299 closing signal SIGTERM
W0217 01:32:05.667000 671409 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 673300 closing signal SIGTERM
W0217 01:32:05.667000 671409 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 673301 closing signal SIGTERM
W0217 01:32:05.667000 671409 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 673302 closing signal SIGTERM
[rank112]:[W217 01:32:05.667143689 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
[rank8]:[W217 01:32:05.264667101 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
[rank56]: Traceback (most recent call last):
[rank56]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train_mem.py", line 4, in
[rank56]: train(attn_implementation="flash_attention_2")
[rank56]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1581, in train
[rank56]: data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args)
[rank56]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1417, in make_supervised_data_module
[rank56]: train_dataset = LazySupervisedMixDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args)
[rank56]: File "/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py", line 1068, in __init__
[rank56]: data_files = glob.glob('/fsx_1/data_curation_output/cyprien/output/wds_caption_llama11b_sg_mmllm_stage1_m2c2v3_sstk_10x_arxiv_pdf_mix_v6/sstk/*/*.tar')
[rank56]: AttributeError: 'function' object has no attribute 'glob'
[rank104]:[W217 01:32:05.957420763 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
[rank32]:[W217 01:32:05.528023617 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
W0217 01:32:05.888000 624291 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 625129 closing signal SIGTERM
W0217 01:32:05.888000 624291 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 625130 closing signal SIGTERM
W0217 01:32:05.889000 624291 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 625131 closing signal SIGTERM
W0217 01:32:05.890000 624291 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 625133 closing signal SIGTERM
W0217 01:32:05.890000 624291 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 625134 closing signal SIGTERM
W0217 01:32:05.890000 624291 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 625135 closing signal SIGTERM
W0217 01:32:05.891000 624291 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 625136 closing signal SIGTERM
[rank88]:[W217 01:32:05.574032740 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
W0217 01:32:05.986000 69771 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 70610 closing signal SIGTERM
W0217 01:32:05.987000 69771 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 70611 closing signal SIGTERM
W0217 01:32:05.988000 69771 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 70612 closing signal SIGTERM
W0217 01:32:05.988000 69771 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 70613 closing signal SIGTERM
W0217 01:32:05.989000 69771 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 70615 closing signal SIGTERM
W0217 01:32:05.989000 69771 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 70616 closing signal SIGTERM
W0217 01:32:05.990000 69771 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 70617 closing signal SIGTERM
W0217 01:32:06.072000 1034984 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1035815 closing signal SIGTERM
W0217 01:32:06.072000 1034984 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1035816 closing signal SIGTERM
W0217 01:32:06.073000 1034984 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1035818 closing signal SIGTERM
W0217 01:32:06.073000 1034984 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1035819 closing signal SIGTERM
W0217 01:32:06.073000 1034984 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1035820 closing signal SIGTERM
W0217 01:32:06.073000 1034984 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1035821 closing signal SIGTERM
W0217 01:32:06.074000 1034984 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1035822 closing signal SIGTERM
W0217 01:32:06.261000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 811381 closing signal SIGTERM
W0217 01:32:06.262000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 811383 closing signal SIGTERM
W0217 01:32:06.262000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 811384 closing signal SIGTERM
W0217 01:32:06.262000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 811385 closing signal SIGTERM
W0217 01:32:06.263000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 811386 closing signal SIGTERM
W0217 01:32:06.263000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 811387 closing signal SIGTERM
W0217 01:32:06.264000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 811388 closing signal SIGTERM
W0217 01:32:06.284000 2019032 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2019158 closing signal SIGTERM
W0217 01:32:06.284000 2019032 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2019159 closing signal SIGTERM
W0217 01:32:06.285000 2019032 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2019160 closing signal SIGTERM
W0217 01:32:06.285000 2019032 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2019161 closing signal SIGTERM
W0217 01:32:06.285000 2019032 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2019163 closing signal SIGTERM
W0217 01:32:06.285000 2019032 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2019164 closing signal SIGTERM
W0217 01:32:06.286000 2019032 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2019165 closing signal SIGTERM
W0217 01:32:06.343000 3877268 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3878098 closing signal SIGTERM
W0217 01:32:06.344000 3877268 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3878099 closing signal SIGTERM
W0217 01:32:06.344000 3877268 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3878100 closing signal SIGTERM
W0217 01:32:06.345000 3877268 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3878101 closing signal SIGTERM
W0217 01:32:06.345000 3877268 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3878102 closing signal SIGTERM
W0217 01:32:06.345000 3877268 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3878104 closing signal SIGTERM
W0217 01:32:06.345000 3877268 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3878105 closing signal SIGTERM
W0217 01:32:06.380000 3567966 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3568809 closing signal SIGTERM
W0217 01:32:06.380000 3567966 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3568811 closing signal SIGTERM
W0217 01:32:06.381000 3567966 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3568812 closing signal SIGTERM
W0217 01:32:06.381000 3567966 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3568813 closing signal SIGTERM
W0217 01:32:06.382000 3567966 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3568814 closing signal SIGTERM
W0217 01:32:06.382000 3567966 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3568815 closing signal SIGTERM
W0217 01:32:06.383000 3567966 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3568816 closing signal SIGTERM
W0217 01:32:06.468000 3205026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3205963 closing signal SIGTERM
W0217 01:32:06.468000 3205026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3205964 closing signal SIGTERM
W0217 01:32:06.469000 3205026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3205965 closing signal SIGTERM
W0217 01:32:06.469000 3205026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3205969 closing signal SIGTERM
W0217 01:32:06.470000 3205026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3205970 closing signal SIGTERM
W0217 01:32:06.470000 3205026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3205971 closing signal SIGTERM
W0217 01:32:06.470000 3205026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3205972 closing signal SIGTERM
W0217 01:32:06.476000 2493811 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2494648 closing signal SIGTERM
W0217 01:32:06.476000 2493811 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2494650 closing signal SIGTERM
W0217 01:32:06.477000 2493811 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2494651 closing signal SIGTERM
W0217 01:32:06.477000 2493811 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2494652 closing signal SIGTERM
W0217 01:32:06.478000 2493811 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2494653 closing signal SIGTERM
W0217 01:32:06.478000 2493811 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2494654 closing signal SIGTERM
W0217 01:32:06.478000 2493811 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2494655 closing signal SIGTERM
W0217 01:32:06.499000 284026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 284886 closing signal SIGTERM
W0217 01:32:06.499000 284026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 284887 closing signal SIGTERM
W0217 01:32:06.500000 284026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 284889 closing signal SIGTERM
W0217 01:32:06.500000 284026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 284890 closing signal SIGTERM
W0217 01:32:06.501000 284026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 284891 closing signal SIGTERM
W0217 01:32:06.501000 284026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 284893 closing signal SIGTERM
[rank72]:[W217 01:32:06.939574899 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
W0217 01:32:06.889000 2016063 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2016899 closing signal SIGTERM
W0217 01:32:06.890000 2016063 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2016900 closing signal SIGTERM
W0217 01:32:06.890000 2016063 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2016901 closing signal SIGTERM
W0217 01:32:06.890000 2016063 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2016902 closing signal SIGTERM
W0217 01:32:06.891000 2016063 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2016903 closing signal SIGTERM
W0217 01:32:06.891000 2016063 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2016904 closing signal SIGTERM
W0217 01:32:06.891000 2016063 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2016906 closing signal SIGTERM
[rank56]:[W217 01:32:06.145364169 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
W0217 01:32:06.976000 4067075 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 4067909 closing signal SIGTERM
W0217 01:32:06.977000 4067075 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 4067910 closing signal SIGTERM
W0217 01:32:06.978000 4067075 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 4067911 closing signal SIGTERM
W0217 01:32:06.978000 4067075 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 4067912 closing signal SIGTERM
W0217 01:32:06.979000 4067075 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 4067914 closing signal SIGTERM
W0217 01:32:06.979000 4067075 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 4067915 closing signal SIGTERM
W0217 01:32:06.980000 4067075 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 4067916 closing signal SIGTERM
W0217 01:32:07.358000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2954556 closing signal SIGTERM
W0217 01:32:07.359000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2954557 closing signal SIGTERM
W0217 01:32:07.360000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2954558 closing signal SIGTERM
W0217 01:32:07.360000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2954559 closing signal SIGTERM
W0217 01:32:07.360000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2954560 closing signal SIGTERM
W0217 01:32:07.360000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2954561 closing signal SIGTERM
W0217 01:32:07.361000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2954562 closing signal SIGTERM
E0217 01:32:07.918000 208189 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:869] failed (exitcode: 1) local_rank: 2 (pid: 209048) of binary: /usr/bin/python3.10
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 269, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
llava/train/train_mem.py FAILED
------------------------------------------------------------
Failures:
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
time : 2025-02-17_01:32:05
host : h100-st-p548xlarge-25.ar-ai-use2.hpcaas
rank : 18 (local_rank: 2)
exitcode : 1 (pid: 209048)
error_file:
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
============================================================
srun: error: h100-st-p548xlarge-25: task 2: Exited with exit code 1
srun: Terminating StepId=335899.0
slurmstepd: error: *** STEP 335899.0 ON h100-st-p548xlarge-6 CANCELLED AT 2025-02-17T01:32:08 ***
W0217 01:32:08.263000 4067075 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.263000 3877268 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.263000 2016063 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.263000 1034984 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.263000 671409 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.263000 2016063 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2016903 closing signal SIGTERM
W0217 01:32:08.263000 2493811 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.263000 4067075 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 4067912 closing signal SIGTERM
W0217 01:32:08.263000 624291 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.263000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.263000 3877268 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3878104 closing signal SIGTERM
W0217 01:32:08.263000 1034984 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1035816 closing signal SIGTERM
W0217 01:32:08.263000 671409 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 673302 closing signal SIGTERM
W0217 01:32:08.263000 69771 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.263000 284026 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.264000 2493811 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2494648 closing signal SIGTERM
W0217 01:32:08.264000 624291 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 625129 closing signal SIGTERM
W0217 01:32:08.263000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.263000 2019032 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.264000 1034984 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1035818 closing signal SIGTERM
W0217 01:32:08.264000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2954556 closing signal SIGTERM
W0217 01:32:08.264000 284026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 284889 closing signal SIGTERM
W0217 01:32:08.264000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 811384 closing signal SIGTERM
W0217 01:32:08.264000 3567966 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.264000 2019032 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2019158 closing signal SIGTERM
W0217 01:32:08.264000 1034984 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1035820 closing signal SIGTERM
W0217 01:32:08.264000 2493811 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2494654 closing signal SIGTERM
W0217 01:32:08.264000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 811385 closing signal SIGTERM
W0217 01:32:08.264000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2954558 closing signal SIGTERM
W0217 01:32:08.264000 1749965 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.264000 3567966 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3568809 closing signal SIGTERM
W0217 01:32:08.265000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 811386 closing signal SIGTERM
W0217 01:32:08.264000 2019032 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2019164 closing signal SIGTERM
W0217 01:32:08.264000 624291 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 625136 closing signal SIGTERM
W0217 01:32:08.265000 2493811 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2494655 closing signal SIGTERM
W0217 01:32:08.264000 3205026 .local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py:704] Received Signals.SIGTERM death signal, shutting down workers
W0217 01:32:08.265000 1749965 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1750796 closing signal SIGTERM
W0217 01:32:08.265000 810550 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 811388 closing signal SIGTERM
W0217 01:32:08.265000 3205026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3205963 closing signal SIGTERM
W0217 01:32:08.265000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2954561 closing signal SIGTERM
W0217 01:32:08.265000 1749965 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1750797 closing signal SIGTERM
W0217 01:32:08.265000 2952825 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2954562 closing signal SIGTERM
W0217 01:32:08.266000 3205026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3205971 closing signal SIGTERM
W0217 01:32:08.266000 1749965 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1750798 closing signal SIGTERM
W0217 01:32:08.266000 3205026 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 3205972 closing signal SIGTERM
W0217 01:32:08.266000 1749965 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1750799 closing signal SIGTERM
W0217 01:32:08.266000 1749965 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1750800 closing signal SIGTERM
W0217 01:32:08.267000 1749965 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1750801 closing signal SIGTERM
W0217 01:32:08.267000 1749965 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1750802 closing signal SIGTERM
W0217 01:32:08.267000 1749965 .local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1750803 closing signal SIGTERM
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 69771 got signal: 15
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 671409 got signal: 15
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 3877268 got signal: 15
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 624291 got signal: 15
srun: error: h100-st-p548xlarge-46: task 4: Exited with exit code 1
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 284026 got signal: 15
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 2019032 got signal: 15
srun: error: h100-st-p548xlarge-164: task 10: Exited with exit code 1
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1034984 got signal: 15
srun: error: h100-st-p548xlarge-40: task 3: Exited with exit code 1
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 3567966 got signal: 15
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 4067075 got signal: 15
srun: error: h100-st-p548xlarge-61: task 5: Exited with exit code 1
srun: error: h100-st-p548xlarge-387: task 15: Exited with exit code 1
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 2016063 got signal: 15
srun: error: h100-st-p548xlarge-315: task 12: Exited with exit code 1
srun: error: h100-st-p548xlarge-62: task 6: Exited with exit code 1
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 810550 got signal: 15
srun: error: h100-st-p548xlarge-6: task 0: Exited with exit code 1
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 3205026 got signal: 15
srun: error: h100-st-p548xlarge-335: task 13: Exited with exit code 1
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 2493811 got signal: 15
srun: error: h100-st-p548xlarge-345: task 14: Exited with exit code 1
srun: error: h100-st-p548xlarge-67: task 8: Exited with exit code 1
srun: error: h100-st-p548xlarge-252: task 11: Exited with exit code 1
srun: error: h100-st-p548xlarge-15: task 1: Exited with exit code 1
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 856, in _invoke_run
run_result = self._monitor_workers(self._worker_group)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 387, in _monitor_workers
result = self._pcontext.wait(0)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 531, in wait
return self._poll()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 861, in _poll
self.close() # terminate all running procs
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 572, in close
self._close(death_sig=death_sig, timeout=timeout)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 909, in _close
handler.proc.wait(time_to_wait)
File "/usr/lib/python3.10/subprocess.py", line 1209, in wait
return self._wait(timeout=timeout)
File "/usr/lib/python3.10/subprocess.py", line 1953, in _wait
time.sleep(delay)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 2952825 got signal: 15
srun: error: h100-st-p548xlarge-63: task 7: Exited with exit code 1
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1749965 got signal: 15
srun: error: h100-st-p548xlarge-93: task 9: Exited with exit code 1
pretrain.sh: 82: python: not found