Upload 20 files

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/care_model.png filter=lfs diff=lfs merge=lfs -text
+assets/carebench.png filter=lfs diff=lfs merge=lfs -text
+assets/comparison.png filter=lfs diff=lfs merge=lfs -text
+assets/demo.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/logo.png filter=lfs diff=lfs merge=lfs -text
+assets/performance.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,43 @@
----
-license: mit
----
+---
+license: mit
+---
+
+<div align="center">
+  <h1 style="margin: 0">
+    <img src="assets/logo.png" style="width:1.5em; vertical-align: middle; display: inline-block; margin: 0" alt="Logo">
+    <span style="vertical-align: middle; display: inline-block; margin: 0"><b>CaReBench: A Fine-grained Benchmark for Video Captioning and Retrieval</b></span>
+  </h1>
+  
+  <p style="margin: 0">
+    Yifan Xu, <a href="https://scholar.google.com/citations?user=evR3uR0AAAAJ">Xinhao Li</a>, Yichun Yang, Desen Meng, Rui Huang, <a href="https://scholar.google.com/citations?user=HEuN8PcAAAAJ">Limin Wang</a>
+  </p>
+  
+  <p align="center">
+    🤗 <a href="https://huggingface.co/MCG-NJU/CaRe-7B">Model</a> &nbsp&nbsp | &nbsp&nbsp 🤗 <a href="https://huggingface.co/datasets/MCG-NJU/CaReBench">Data</a> &nbsp&nbsp｜ &nbsp&nbsp 📑 <a href="https://arxiv.org/pdf/2501.00513">Paper</a> &nbsp&nbsp 
+  </p>
+</div>
+
+
+## 📝 Introduction
+
+This is Tarsier 7B trained with *Retrieval Adaptation*. Refer to [our paper](https://arxiv.org/pdf/2501.00513) for details.
+
+## Usage
+
+Loading from the huggingface remote path is not tested. It is **recommended** to download this checkpoint to your local environment to prevent potential bugs.
+
+### For Retrieval Tasks
+```python
+from utils.video import read_frames_decord
+from models.modeling_encoders import AutoEncoder
+from torch.nn.functional import cosine_similarity
+
+encoder = AutoEncoder.from_pretrained('path/to/checkpoints/Tarsier-7B-RA')
+frames = read_frames_decord(video_path='assets/demo.mp4', num_frames=32)
+text = "This video features a man slicing tomatoes in the kitchen."
+vision_emb = encoder.encode_vision(frames.unsqueeze(0))
+text_emb = encoder.encode_text(text)
+print(f'Vision embedding shape: {vision_emb.shape}')
+print(f'Text embedding shape: {text_emb.shape}')
+print(f'Cosine similarity: {cosine_similarity(vision_emb, text_emb)}')
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image>": 32000
+}

assets/demo.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c0577c7ddb27230f46f5186c51b3220d8902595edc58607298381bc8629c50
+size 1049106

config.json

@@ -0,0 +1,44 @@
+{
+  "add_transformer_projector": false,
+  "architectures": [
+    "TarsierForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_new_idx": 32003,
+  "image_newline_idx": 32002,
+  "image_token_index": 32000,
+  "model_type": "llava",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-05,
+    "torch_dtype": "float16",
+    "use_bpex_rmsnorm": true,
+    "use_bpex_rotary": true,
+    "use_cache": false,
+    "use_ft_flash_attn": true,
+    "vocab_size": 32064
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "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 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.0",
+  "use_cache": false
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924f7dff6257a1434d718d4ab6eacaa3add85d16fb66423e1df0de401ef8cccc
+size 4992930688

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9d1e7fc8e544004fdc29889d834e6d8300442cfb1dd85423c6bdb62434e26d2
+size 4957878552

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d067535c02d656a5ad92bb3e824420621a6c3cd4ec12e36beaebdf7773f55b6
+size 4176137496

model.safetensors.index.json

@@ -0,0 +1,693 @@
+{
+  "metadata": {
+    "total_size": 14126854144
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.norm.weight": "model-00003-of-00003.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00003.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00003.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00003.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00003.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
+  }
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "image_token": "<image>",
+  "patch_size": 14,
+  "processor_class": "LlavaProcessor",
+  "vision_feature_select_strategy": "default"
+}

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": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": true,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}