Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "/group/40079/yinanzhou/LLaVA-NeXT/checkpoints/high/llavanext-model_zoo_InternViT-300M-448px-from-InternVL2-8b-model_zoo_Qwen_Qwen2-7B-Instruct-ln_mlp2x_gelu-mplug-PCG-full5M-pretrain-decode_correct-no-padding-48npu--qwen_1_5",
+  "architectures": [
+    "LlavaQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "best_resolution_select_mode": "nearest_no_padding",
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_aspect_ratio": "anyres_max_9",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": "16",
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mm_hidden_size": 4096,
+  "mm_newline_position": "one_token",
+  "mm_patch_merge_type": "linebreak",
+  "mm_projector_lr": null,
+  "mm_projector_type": "ln_mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower": "model_zoo/InternViT-300M-448px-from-InternVL2-8b",
+  "mm_vision_tower_lr": 2e-06,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 6144,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": null,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a50440ed16cf6adef68528c18d16661bf8d25b7d4bf7224a2ff695830a7c7d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa1dc43a11bb5716225a6d7d7cf0f87def59a0afdbd9450cf6a99697fd5535b
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fceab2ad8504b58bcf7efd0ef02fcb51ce36af2ba35f77fe5e073f6c8330253
+size 4994017752

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60e85624300442c4dcad982e0bb4c5ad404d4d0ed4e3e3468fbaf118fd17b6a7
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,692 @@
+{
+  "metadata": {
+    "total_size": 15894338560
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.mm_projector.0.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector.1.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.1.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector.3.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.3.weight": "model-00003-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.embeddings.class_embedding": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.embeddings.patch_embedding.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.embeddings.position_embedding": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.0.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.1.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.10.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.11.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.12.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.13.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.14.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.15.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.16.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.17.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.18.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.19.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.2.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.20.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.21.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.22.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.23.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.3.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.4.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.5.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.6.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.7.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.8.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.ls1": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.ls2": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.layers.9.norm2.weight": "model-00003-of-00004.safetensors"
+  }
+}

runs/Nov05_04-18-19_vc-816965669-20241103-c5e42cfa-worker-0/events.out.tfevents.1730751668.vc-816965669-20241103-c5e42cfa-worker-0.908.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a7c43b0696eaa9e91a0d207099ebc067418cfa60f64538b9c4fdccadd0b2c1
+size 1190046

runs/Nov07_22-42-46_vc-816965669-20241103-15d9f582-worker-0/events.out.tfevents.1730990880.vc-816965669-20241103-15d9f582-worker-0.908.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfddd6645e777be5c0368c8dd1fd057bd7b0fd50b0b3e6a0225d43dc535b6735
+size 374338

runs/Nov08_19-08-11_vc-816965669-20241103-979a5ed3-worker-0/events.out.tfevents.1731064385.vc-816965669-20241103-979a5ed3-worker-0.908.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec29de0dcfde0d1abe765f5c394071f4bf0d7f2c0239b91f46735b698a7e346
+size 36738

runs/Nov08_20-52-22_vc-816965669-20241103-4c46368f-worker-0/events.out.tfevents.1731070650.vc-816965669-20241103-4c46368f-worker-0.911.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a55c2309c7414712b33a875cc6df6039c4c3104be70ac1589052b2f73ae0fbb
+size 36738

runs/Nov08_22-31-37_vc-816965669-20241103-bb0ca7b9-worker-0/events.out.tfevents.1731076580.vc-816965669-20241103-bb0ca7b9-worker-0.911.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd1c46b5d9b73c8bf97672167144448872d8d81de555cf491a9a1fe7c2fcf80
+size 36738

runs/Nov09_12-44-34_vc-816971722-20241108-8d67798f-worker-0/events.out.tfevents.1731127745.vc-816971722-20241108-8d67798f-worker-0.944.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee1c8e1639c4e55d742f6c19072d37c1534af0ef774efdce62168f0dfbf4d35
+size 36759

runs/Nov09_13-51-51_vc-816971722-20241108-a9b6b871-worker-0/events.out.tfevents.1731131789.vc-816971722-20241108-a9b6b871-worker-0.937.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f07d72215426f0301800458348153364dc0d3177057281ffe9cd3b693eb11c27
+size 36759

runs/Nov09_15-02-47_vc-816971722-20241108-d7823f88-worker-0/events.out.tfevents.1731136035.vc-816971722-20241108-d7823f88-worker-0.937.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb59fb71be6351f570da89a78924bf57f356a592593738df90345f53855e0bd
+size 36759

runs/Nov09_16-15-14_vc-816971722-20241108-b5ed0927-worker-0/events.out.tfevents.1731140382.vc-816971722-20241108-b5ed0927-worker-0.942.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3921923c82701e90b72584131762e80ec3f1fecc20570763bfc66978b5e93a5c
+size 36759

runs/Nov09_17-22-57_vc-816971722-20241108-994b0f21-worker-0/events.out.tfevents.1731144442.vc-816971722-20241108-994b0f21-worker-0.938.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d01afff04a7c2184a30f237893670b300918f6290e56737c3c139a9639d9aeac
+size 36759

runs/Nov09_18-30-43_vc-816971722-20241108-9ddee8a6-worker-0/events.out.tfevents.1731148516.vc-816971722-20241108-9ddee8a6-worker-0.941.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a2b93b25857110e1dffc1bd30eb0f4c7f157be714166f9f29c0670e87666d3
+size 36759

runs/Nov09_19-38-05_vc-816971722-20241108-b19e0f1b-worker-0/events.out.tfevents.1731152566.vc-816971722-20241108-b19e0f1b-worker-0.939.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16cdcf7998b4ca837805a1c0f015e7952b860a3ef5849d222d2195532002bc4c
+size 26277

runs/Nov10_10-04-15_vc-816971722-20241109-bb0477a1-worker-0/events.out.tfevents.1731204538.vc-816971722-20241109-bb0477a1-worker-0.938.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4dcfbf629c2a3b96d82120c812c14af0e44c2c7c10c520e1858231168e8196
+size 36759

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 6144,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6149fa3bfb8acfba06aa03d3e5472016697c9d338fae91b822ce41f038e38c75
+size 7992