diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json"
--- "a/model.safetensors.index.json"
+++ "b/model.safetensors.index.json"
@@ -1,8 +1,399 @@
 {
   "metadata": {
-    "total_size": 14126198784
+    "total_size": 14732558336
   },
   "weight_map": {
+    "image_tower.vision_model.embeddings.class_embedding": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.post_layernorm.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.post_layernorm.weight": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00003.safetensors",
+    "image_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00003.safetensors",
     "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",
@@ -30,7 +421,7 @@
     "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.q_proj.weight": "model-00002-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",
@@ -122,33 +513,33 @@
     "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.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-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.post_attention_layernorm.weight": "model-00003-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.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-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.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-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",
@@ -275,419 +666,419 @@
     "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.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-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.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-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.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-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.embeddings.class_embedding": "model-00001-of-00003.safetensors",
-    "vision_tower.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.embeddings.position_embedding.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.layer_norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.layer_norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.layer_norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.layer_norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.post_layernorm.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.post_layernorm.weight": "model-00001-of-00003.safetensors",
-    "vision_tower.pre_layrnorm.bias": "model-00001-of-00003.safetensors",
-    "vision_tower.pre_layrnorm.weight": "model-00001-of-00003.safetensors"
+    "video_tower.vision_model.embeddings.class_embedding": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.post_layernorm.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.post_layernorm.weight": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00003.safetensors",
+    "video_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00003.safetensors"
   }
 }