diff --git a/cache_dir/models--LanguageBind--LanguageBind_Image/.no_exist/e04d5e400f9852d1d95d212d14ad7fb27ffed493/adapter_config.json b/cache_dir/models--LanguageBind--LanguageBind_Image/.no_exist/e04d5e400f9852d1d95d212d14ad7fb27ffed493/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/cache_dir/models--LanguageBind--LanguageBind_Image/.no_exist/e04d5e400f9852d1d95d212d14ad7fb27ffed493/model.safetensors b/cache_dir/models--LanguageBind--LanguageBind_Image/.no_exist/e04d5e400f9852d1d95d212d14ad7fb27ffed493/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/cache_dir/models--LanguageBind--LanguageBind_Image/.no_exist/e04d5e400f9852d1d95d212d14ad7fb27ffed493/model.safetensors.index.json b/cache_dir/models--LanguageBind--LanguageBind_Image/.no_exist/e04d5e400f9852d1d95d212d14ad7fb27ffed493/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/cache_dir/models--LanguageBind--LanguageBind_Image/refs/main b/cache_dir/models--LanguageBind--LanguageBind_Image/refs/main
new file mode 100644
index 0000000000000000000000000000000000000000..116611c7288d3603337b2f59a2c54f0816c840e2
--- /dev/null
+++ b/cache_dir/models--LanguageBind--LanguageBind_Image/refs/main
@@ -0,0 +1 @@
+e04d5e400f9852d1d95d212d14ad7fb27ffed493
\ No newline at end of file
diff --git a/cache_dir/models--LanguageBind--LanguageBind_Image/snapshots/e04d5e400f9852d1d95d212d14ad7fb27ffed493/config.json b/cache_dir/models--LanguageBind--LanguageBind_Image/snapshots/e04d5e400f9852d1d95d212d14ad7fb27ffed493/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..489a204fbbf88be178913631a47eabbcb6103709
--- /dev/null
+++ b/cache_dir/models--LanguageBind--LanguageBind_Image/snapshots/e04d5e400f9852d1d95d212d14ad7fb27ffed493/config.json
@@ -0,0 +1,173 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "LanguageBindImage",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_time_attn": false,
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.29.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "lora_r": 0,
+    "lora_alpha": 16,
+    "lora_dropout": 0.1,
+    "add_time_attn": false,
+    "num_frames": 1,
+    "num_mel_bins": 0,
+    "target_length": 0,
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.29.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}
diff --git a/cache_dir/models--LanguageBind--LanguageBind_Video/.no_exist/499d15b90211c6e622cc7f5d12655f5e787f12a5/adapter_config.json b/cache_dir/models--LanguageBind--LanguageBind_Video/.no_exist/499d15b90211c6e622cc7f5d12655f5e787f12a5/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/cache_dir/models--LanguageBind--LanguageBind_Video/.no_exist/499d15b90211c6e622cc7f5d12655f5e787f12a5/model.safetensors b/cache_dir/models--LanguageBind--LanguageBind_Video/.no_exist/499d15b90211c6e622cc7f5d12655f5e787f12a5/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/cache_dir/models--LanguageBind--LanguageBind_Video/.no_exist/499d15b90211c6e622cc7f5d12655f5e787f12a5/model.safetensors.index.json b/cache_dir/models--LanguageBind--LanguageBind_Video/.no_exist/499d15b90211c6e622cc7f5d12655f5e787f12a5/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/cache_dir/models--LanguageBind--LanguageBind_Video/refs/main b/cache_dir/models--LanguageBind--LanguageBind_Video/refs/main
new file mode 100644
index 0000000000000000000000000000000000000000..a69384ec18f7d03ed720031d47859875f3bb546a
--- /dev/null
+++ b/cache_dir/models--LanguageBind--LanguageBind_Video/refs/main
@@ -0,0 +1 @@
+499d15b90211c6e622cc7f5d12655f5e787f12a5
\ No newline at end of file
diff --git a/cache_dir/models--LanguageBind--LanguageBind_Video/snapshots/499d15b90211c6e622cc7f5d12655f5e787f12a5/config.json b/cache_dir/models--LanguageBind--LanguageBind_Video/snapshots/499d15b90211c6e622cc7f5d12655f5e787f12a5/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0d6332792bdd18d4bed8b991b763724ce021acff
--- /dev/null
+++ b/cache_dir/models--LanguageBind--LanguageBind_Video/snapshots/499d15b90211c6e622cc7f5d12655f5e787f12a5/config.json
@@ -0,0 +1,173 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "LanguageBindVideo",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_time_attn": false,
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.29.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "lora_r": 16,
+    "lora_alpha": 16,
+    "lora_dropout": 0.1,
+    "add_time_attn": true,
+    "num_frames": 8,
+    "num_mel_bins": 0,
+    "target_length": 0,
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.29.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}
diff --git a/models--LanguageBind--Video-LLaVA-7B/.no_exist/d7348faa006fdf93d04fd0df093d8a03b61dc25c/adapter_config.json b/models--LanguageBind--Video-LLaVA-7B/.no_exist/d7348faa006fdf93d04fd0df093d8a03b61dc25c/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/models--LanguageBind--Video-LLaVA-7B/.no_exist/d7348faa006fdf93d04fd0df093d8a03b61dc25c/model.safetensors b/models--LanguageBind--Video-LLaVA-7B/.no_exist/d7348faa006fdf93d04fd0df093d8a03b61dc25c/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/models--LanguageBind--Video-LLaVA-7B/.no_exist/d7348faa006fdf93d04fd0df093d8a03b61dc25c/model.safetensors.index.json b/models--LanguageBind--Video-LLaVA-7B/.no_exist/d7348faa006fdf93d04fd0df093d8a03b61dc25c/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/models--LanguageBind--Video-LLaVA-7B/.no_exist/d7348faa006fdf93d04fd0df093d8a03b61dc25c/pytorch_model.bin b/models--LanguageBind--Video-LLaVA-7B/.no_exist/d7348faa006fdf93d04fd0df093d8a03b61dc25c/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/models--LanguageBind--Video-LLaVA-7B/refs/main b/models--LanguageBind--Video-LLaVA-7B/refs/main
new file mode 100644
index 0000000000000000000000000000000000000000..28e12bd2640e51f9f72cbd8bbfa32b55941c3b31
--- /dev/null
+++ b/models--LanguageBind--Video-LLaVA-7B/refs/main
@@ -0,0 +1 @@
+d7348faa006fdf93d04fd0df093d8a03b61dc25c
\ No newline at end of file
diff --git a/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/config.json b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..3ba1c3fcc4dfa9859962307992f660144cbdf40e
--- /dev/null
+++ b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/config.json
@@ -0,0 +1,43 @@
+{
+  "X": [
+    "Video",
+    "Image"
+  ],
+  "_name_or_path": "lmsys/vicuna-7b-v1.5",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "image_grid_pinpoints": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_image_tower": "LanguageBind/LanguageBind_Image",
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_x_patch_token": false,
+  "mm_use_x_start_end": false,
+  "mm_video_tower": "LanguageBind/LanguageBind_Video",
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "model_type": "llava",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}
diff --git a/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/generation_config.json b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..57dbab308581e71f2adb7e9335aad7bc02cf3bb4
--- /dev/null
+++ b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.31.0"
+}
diff --git a/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/pytorch_model.bin.index.json b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/pytorch_model.bin.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..385767f1597c63487ed049e085abf3757a24a3f9
--- /dev/null
+++ b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/pytorch_model.bin.index.json
@@ -0,0 +1,1380 @@
+{
+  "metadata": {
+    "total_size": 14933528576
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.image_tower.image_tower.embeddings.class_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.embeddings.patch_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.embeddings.position_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.post_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.post_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.pre_layrnorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.image_tower.image_tower.pre_layrnorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.mm_projector.0.bias": "pytorch_model-00002-of-00002.bin",
+    "model.mm_projector.0.weight": "pytorch_model-00002-of-00002.bin",
+    "model.mm_projector.2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.mm_projector.2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.embeddings.class_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.embeddings.patch_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.embeddings.position_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.0.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.1.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.10.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.11.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.12.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.13.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.14.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.15.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.16.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.17.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.18.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.19.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.2.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.20.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.21.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.22.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.23.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.3.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.4.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.5.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.6.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.7.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.8.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.temporal_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.temporal_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.temporal_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.temporal_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.temporal_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.temporal_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.temporal_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.temporal_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.temporal_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.temporal_layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.encoder.layers.9.temporal_layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.post_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.post_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.pre_layrnorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.video_tower.video_tower.pre_layrnorm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}
diff --git a/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/special_tokens_map.json b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/tokenizer.model b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/tokenizer_config.json b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..740756b4bef305e27d0bb4d2e1a40dd8847797f7
--- /dev/null
+++ b/models--LanguageBind--Video-LLaVA-7B/snapshots/d7348faa006fdf93d04fd0df093d8a03b61dc25c/tokenizer_config.json
@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}