sharpenb's picture
Upload folder using huggingface_hub (#1)
ca656dc verified
{
"_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelsc4kbe8er6gy6_eei",
"architectures": [
"LlavaQwen2ForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_llava_qwen2.LlavaQwen2Config",
"AutoModelForCausalLM": "modeling_llava_qwen2.LlavaQwen2ForCausalLM"
},
"bos_token_id": 151645,
"eos_token_id": 151645,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 1024,
"image_aspect_ratio": "pad",
"initializer_range": 0.02,
"intermediate_size": 2816,
"language_model": "vilm/Quyen-SE-v0.1",
"max_position_embeddings": 32768,
"max_window_layers": 21,
"mm_hidden_size": 1152,
"mm_projector_lr": null,
"mm_projector_type": "mlp2x_gelu",
"mm_vision_tower": "google/siglip-so400m-patch14-384",
"model_type": "llava-qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": false,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": [
"lm_head"
],
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 4096,
"tokenizer_padding_side": "right",
"torch_dtype": "float16",
"transformers_version": "4.42.4",
"tune_mm_mlp_adapter": false,
"use_cache": false,
"use_mm_proj": true,
"use_sliding_window": false,
"vocab_size": 151936
}