Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,226 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct-1M",
+  "architectures": [
+    "LlavaQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dual_chunk_attention_config": {
+    "chunk_size": 262144,
+    "local_size": 8192,
+    "original_max_position_embeddings": 262144
+  },
+  "eos_token_id": 151645,
+  "frame_aspect_ratio": "square",
+  "frame_grid_pinpoints": null,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_aspect_ratio": "anyres_nopad",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": [
+    [
+      224,
+      224
+    ],
+    [
+      224,
+      448
+    ],
+    [
+      224,
+      672
+    ],
+    [
+      224,
+      896
+    ],
+    [
+      224,
+      1120
+    ],
+    [
+      224,
+      1344
+    ],
+    [
+      448,
+      224
+    ],
+    [
+      448,
+      448
+    ],
+    [
+      448,
+      672
+    ],
+    [
+      448,
+      896
+    ],
+    [
+      448,
+      1120
+    ],
+    [
+      448,
+      1344
+    ],
+    [
+      672,
+      224
+    ],
+    [
+      672,
+      448
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      672,
+      896
+    ],
+    [
+      672,
+      1120
+    ],
+    [
+      672,
+      1344
+    ],
+    [
+      896,
+      224
+    ],
+    [
+      896,
+      448
+    ],
+    [
+      896,
+      672
+    ],
+    [
+      896,
+      896
+    ],
+    [
+      896,
+      1120
+    ],
+    [
+      896,
+      1344
+    ],
+    [
+      1120,
+      224
+    ],
+    [
+      1120,
+      448
+    ],
+    [
+      1120,
+      672
+    ],
+    [
+      1120,
+      896
+    ],
+    [
+      1120,
+      1120
+    ],
+    [
+      1120,
+      1344
+    ],
+    [
+      1344,
+      224
+    ],
+    [
+      1344,
+      448
+    ],
+    [
+      1344,
+      672
+    ],
+    [
+      1344,
+      896
+    ],
+    [
+      1344,
+      1120
+    ],
+    [
+      1344,
+      1344
+    ]
+  ],
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "llm_compress_layer_list": [
+    8,
+    16,
+    24
+  ],
+  "llm_compress_type": "attention",
+  "llm_image_token_ratio_list": [
+    1.0,
+    0.5,
+    0.25,
+    0.125
+  ],
+  "max_num_pixels": 14745600000,
+  "max_position_embeddings": 1010000,
+  "max_window_layers": 28,
+  "min_slow_num_frames": 4,
+  "mm_close_init": true,
+  "mm_hidden_size": 1024,
+  "mm_llm_compress": false,
+  "mm_local_num_frames": 4,
+  "mm_newline_position": "nothing",
+  "mm_num_compress_latents": 128,
+  "mm_num_compress_query_type": "learnable",
+  "mm_patch_merge_type": "spatial_nopad",
+  "mm_pos_num_frames": 8,
+  "mm_projector_lr": null,
+  "mm_projector_type": "tome16_mlp_hd64",
+  "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": -2,
+  "mm_vision_tower": "umt-large",
+  "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-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 32768,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_encode_type": "video_image",
+  "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": "4.39.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402ab53e5548ab0280787b8c798d8de898606a243077eb382a32532957968691
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:351f5667fe9aef14d63bda05ff524e252d689d488476a51987cff742b6916181
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c564fd7ba8931a9a508e994cdddfb6d648f31ec7aab80d652827be6d48bda77
+size 4944910024

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76cb93ba1f18e4ff122dfbad0e26d1042c4bb38bf3feb7d5978c0d3f18f4250e
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,653 @@
+{
+  "metadata": {
+    "total_size": 15845235712
+  },
+  "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.mlp.0.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.mlp.0.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector.mlp.2.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.mlp.2.weight": "model-00003-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.0.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.1.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.10.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.11.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.12.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.13.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.14.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.15.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.16.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.17.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.18.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.19.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.2.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.20.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.21.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.22.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.3.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.4.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.5.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.6.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.7.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.8.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.attn.q_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.attn.v_bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.blocks.9.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.patch_embed.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.patch_embed.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.vision_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.encoder.vision_layernorm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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 +1,208 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "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 sha256:5db9a8219e0b7d0f6a81308ff9603ae2223695af2a7a929a57176e67edb35f77
+size 7416