Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,23 @@
+---
+language:
+- en
+library_name: transformers
+license: apache-2.0
+pipeline_tag: image-text-to-text
+tags:
+- multimodal
+- mlx
+---
+
+# mlx-community/Qwen2-VL-7B-Instruct-bf16
+This model was converted to MLX format from [`Qwen/Qwen2-VL-7B-Instruct`]() using mlx-vlm version **0.0.13**.
+Refer to the [original model card](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model mlx-community/Qwen2-VL-7B-Instruct-bf16 --max-tokens 100 --temp 0.0
+```

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,52 @@
+{
+    "architectures": [
+        "Qwen2VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "image_token_id": 151655,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "model_type": "qwen2_vl",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "type": "mrope",
+        "mrope_section": [
+            16,
+            24,
+            24
+        ]
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.41.2",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": 151656,
+    "vision_config": {
+        "depth": 32,
+        "embed_dim": 1280,
+        "mlp_ratio": 4,
+        "num_heads": 16,
+        "in_chans": 3,
+        "hidden_size": 3584,
+        "patch_size": 14,
+        "spatial_merge_size": 2,
+        "spatial_patch_size": 14,
+        "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b504447ce7ff43c996eb1f3b60134fa9bbd15a8d2e5a50c2f5f4c3f92264a48
+size 5296989658

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b45a85f02e71e089be69e45f16a27d432ece92007fb4eb5dcb8906f1415df2
+size 5263079242

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314b39248e30bf9f48291c278eb28d12b84502c31aa6eb38dc547e10838b7894
+size 4932774729

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbadb9a812beb9c2b77f6db61ebed0bd23d31c6e3d043ad1ef98476c54bd7786
+size 1089994894

model.safetensors.index.json

@@ -0,0 +1,737 @@
+{
+    "metadata": {
+        "total_size": 16582751232
+    },
+    "weight_map": {
+        "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+        "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "language_model.model.norm.weight": "model-00003-of-00004.safetensors",
+        "vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.merger.ln_q.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+        "vision_tower.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+        "vision_tower.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+    }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "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
+    }
+  },
+  "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": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}