初始化项目，由ModelHub XC社区提供模型

Model: YuchengShi/LLaVA-v1.5-7B-Plant-Leaf-Diseases-Detection
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+tags: []
+pipeline_tag: image-text-to-text
+---
+
+# Fine-Grained Visual Classification on Plant Leaf Diseases  
+
+Project Page: [SelfSynthX](https://github.com/sycny/SelfSynthX).
+
+Paper on arXiv: [Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data](https://arxiv.org/abs/2502.14044)
+  
+
+This model is a fine-tuned multimodal foundation model based on [LLaVA-1.5-7B-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf), optimized for detecting and explaining plant leaf diseases using the Plant disease dataset.
+
+## Key Details  
+
+- **Base Model:** LLaVA-1.5-7B  
+- **Dataset:** Healthy and diseased leaves across multiple plant species
+- **Innovation:**  
+  - **Self-Synthesized Data:** Extracts and describes disease-specific visual symptoms using the Information Bottleneck principle.  
+  - **Iterative Fine-Tuning:** Uses reward model-free rejection sampling to improve classification accuracy and explanation quality.  
+- **Intended Use:** Identification of plant leaf diseases with human-verifiable symptom descriptions.
+
+## How to Use  
+
+```python
+import requests
+from PIL import Image
+import torch
+from transformers import AutoProcessor, LlavaForConditionalGeneration
+
+model_id = "YuchengShi/LLaVA-v1.5-7B-Plant-Leaf-Diseases-Detection"
+model = LlavaForConditionalGeneration.from_pretrained(
+    model_id, 
+    torch_dtype=torch.float16, 
+    low_cpu_mem_usage=True,
+).to("cuda")
+processor = AutoProcessor.from_pretrained(model_id)
+
+conversation = [
+    {
+      "role": "user",
+      "content": [
+          {"type": "text", "text": "What disease does this leaf have?"},
+          {"type": "image"},
+        ],
+    },
+]
+prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
+image_file = "plant-disease/test1.png"
+raw_image = Image.open(requests.get(image_file, stream=True).raw)
+inputs = processor(images=raw_image, text=prompt, return_tensors='pt').to("cuda", torch.float16)
+
+output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
+print(processor.decode(output[0][2:], skip_special_tokens=True))
+```
+
+## Training & Evaluation  
+
+- **Training:** Fine-tuned using LoRA on PlantVillage with iterative rejection sampling.  
+- **Evaluation:** Demonstrates superior accuracy and robust, interpretable explanations compared to baseline models.
+
+## Citation  
+
+If you use this model, please cite:  
+
+```bibtex
+@inproceedings{
+  shi2025enhancing,
+  title={Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data},
+  author={Yucheng Shi and Quanzheng Li and Jin Sun and Xiang Li and Ninghao Liu},
+  booktitle={The Thirteenth International Conference on Learning Representations},
+  year={2025},
+  url={https://openreview.net/forum?id=lHbLpwbEyt}
+}
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}"
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "/home/local/PARTNERS/ys670/camca/ys670/checkpoint-4/PLD-2024-11-15/merged_model",
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_token_index": 32000,
+  "model_type": "llava",
+  "pad_token_id": 32001,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "rms_norm_eps": 1e-05,
+    "torch_dtype": "float16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 32001,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7999979a90cbe72c8361e03acccb597f2676708c581eeebf8082c80cbf4a6a25
+size 4881089608

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702b0268d545e2db1e0d37a06b7b19a558aa53155dc5fefb43d168686dcc5140
+size 4857207648

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c61ccc5ccd74e0d85b6d3af49d6b82ade003ad1062070fe0437c49524d3f2e
+size 4857207704

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af60d18e9f1083f7a3add029d0b161d532a54b9e90ef4bb3c15717c510b00014
+size 4857207704

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e95d716202ce51faa6df3dc4a25e73a8e2c00404a3c0c2d7d495aca16c33eb8
+size 4857207704

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c872e3b5db999e567615355e41c5f3df50af0b886bfb13ca7f9ab1c5890a3a4
+size 3943879896

model.safetensors.index.json

@@ -0,0 +1,693 @@
+{
+  "metadata": {
+    "total_size": 28253708288
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.norm.weight": "model-00006-of-00006.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00006.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00006.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00006.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00006.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}