初始化项目，由ModelHub XC社区提供模型

Model: prithivMLmods/Enesidaon-VLR-7B-no-Thinking
Source: Original Platform

.gitattributes

@@ -0,0 +1,51 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+merges.txt filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+vocab.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,113 @@
+---
+license: apache-2.0
+language:
+- en
+- zh
+base_model:
+- Qwen/Qwen2.5-VL-7B-Instruct
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- text-generation-inference
+- trl
+- ocr
+- vision-language
+- reasoning
+- grounded-visual-reasoning
+- sft
+- grpo
+- no-thinking
+- code
+- thinking=0
+---
+
+![1.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/yiFI0lMGM7SdkmwS09BaZ.png)
+
+# **Enesidaon-VLR-7B-no-Thinking**
+
+> The **Enesidaon-VLR-7B-no-Thinking** model is a high-fidelity vision-language reasoning (experimental) model designed for fine-grained multimodal comprehension. Built on top of **Qwen2.5-VL-7B-Instruct**, this model improves image captioning, sampled video reasoning, and detailed document understanding. Unlike standard approaches, it explicitly grounds its textual reasoning steps to visual coordinates, enabling precise and explainable multimodal reasoning. The model is trained using supervised fine-tuning (SFT) on visually-grounded reasoning traces and further optimized via GRPO reinforcement learning, resulting in superior chain-of-thought reasoning without overthinking or unnecessary hallucinations.
+
+## Key Enhancements
+
+* **Visually-Grounded Reasoning and Explanation**: Explicitly anchors reasoning chains to image regions and document elements for transparent, explainable multimodal outputs.
+* **Advanced Image Captioning**: Produces context-aware, detailed captions with grounded reasoning for improved visual understanding.
+* **Sampled Video Reasoning**: Handles long-duration video inputs with temporal reasoning for content summarization and QA.
+* **Context-Aware Document Analysis**: Excels in document retrieval, structured and unstructured content extraction, and analytical content recognition.
+* **Fine-Grained Visual Grounding**: Enhanced capability for multimodal linking across charts, tables, and graphical elements with spatial grounding.
+* **Reinforcement-Learned Reasoning**: Trained with GRPO to incentivize accurate, grounded reasoning aligned with visual cues.
+* **State-of-the-Art Benchmarking**: Competitive results on OCR, visual QA, and reasoning tasks including DocVQA, MathVista, RealWorldQA, and MTVQA.
+
+## Quick Start with Transformers
+
+```python
+from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
+from qwen_vl_utils import process_vision_info
+
+model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+    "prithivMLmods/Enesidaon-VLR-7B-no-Thinking", torch_dtype="auto", device_map="auto"
+)
+
+processor = AutoProcessor.from_pretrained("prithivMLmods/Enesidaon-VLR-7B-no-Thinking")
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
+            },
+            {"type": "text", "text": "Describe this image with reasoning."},
+        ],
+    }
+]
+
+text = processor.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+image_inputs, video_inputs = process_vision_info(messages)
+inputs = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+inputs = inputs.to("cuda")
+
+generated_ids = model.generate(**inputs, max_new_tokens=128)
+generated_ids_trimmed = [
+    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_text = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print(output_text)
+```
+
+## Intended Use
+
+This model is intended for:
+
+* Grounded visual reasoning with spatially-aligned chain-of-thought explanations.
+* Accurate, explainable image captioning and video reasoning.
+* Multimodal document analysis with visually-referenced reasoning steps.
+* Analytical content recognition, table/chart interpretation, and structured extraction.
+* Multilingual reasoning over documents and visual scenes for global applications.
+* Educational and enterprise solutions requiring step-by-step reasoning transparency.
+* Robotic and mobile device automation with vision-guided contextual decision-making.
+
+## Limitations
+
+* May require high memory for long videos and complex document inputs.
+* Performance can degrade with extremely low-resolution or heavily occluded images.
+* Not fully optimized for real-time inference on low-resource edge devices.
+* Visual token configurations significantly impact grounded reasoning performance.
+* Some rare cases of reasoning drift or incomplete grounding.
+
+## References
+
+* **YaRN: Efficient Context Window Extension of Large Language Models**
+* **Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution**
+* **Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond**
+* **A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy**

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
+}

chat_template.jinja

@@ -0,0 +1,7 @@
+{% 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
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,136 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "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": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "image_token_id": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 128000,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "max_length": 128000,
+  "pad_token_id": 151643,
+  "transformers_version": "4.54.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e731b81dc10570d949b7a5920869283be95fb6661ffc6f9ae160a0490440340
+size 4997621312

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9ee6c336c724a10986452932958fd7ebdeaf461cd85c74a7c42b50c87f0a13
+size 4269312608

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0357ffac8d7c59b37da64be84683a0fdf54a07f42f622bbe8a1911475c6f1bf9
+size 4883105448

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55bba35b8d139536100ca9dc62dc6c15b4970ab24726784d9fc51ce8bc48ca4
+size 2434375184

model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-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-00002-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-00002-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00003-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-00004-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-00002-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-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-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-00004-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-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-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-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-00004-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-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-00001-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-00004-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-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-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-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-00004-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-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-00004-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-00004-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-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-00004-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-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-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-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-00004-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-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-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-00002-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-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-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-00003-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-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-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-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-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-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-00002-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-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-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-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-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-00004-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-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-00001-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-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-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-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-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-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-00002-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00003-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-00004-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-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-00003-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-00004-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-00003-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-00003-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-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-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-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-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-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-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-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00002-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00002-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00002-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00003-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00003-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00003-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00003-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,37 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 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:e04081d680d5bb294b2e57aea5b3aa1256d9e06263e907917fc241c5adc2fbe4
+size 11422163

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}