Upload AriaForConditionalGeneration

README.md

@@ -1,8 +1,8 @@
 ---
-license: apache-2.0
 language:
 - en
 library_name: transformers
+license: apache-2.0
 pipeline_tag: image-text-to-text
 tags:
 - multimodal

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "rhymes-ai/Aria",
   "architectures": [
     "AriaForConditionalGeneration"
   ],
@@ -8,17 +9,18 @@
   },
   "ignore_index": -100,
   "image_token_index": 9,
+  "initializer_range": 0.02,
   "model_type": "aria",
+  "pad_token_id": 2,
   "projector_patch_to_query_dict": {
     "1225": 128,
     "4900": 256
   },
   "text_config": {
     "hidden_size": 2560,
-    "intermediate_size": 13568,
+    "intermediate_size": 1664,
     "max_position_embeddings": 65536,
-    "model_type": "aria_moe_lm",
-    "moe_intermediate_size": 1664,
+    "model_type": "aria_text",
     "moe_num_experts": 64,
     "moe_topk": 6,
     "num_attention_heads": 20,
@@ -29,21 +31,19 @@
     "vocab_size": 100352
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.0",
-  "_attn_implementation": "flash_attention_2",
+  "transformers_version": "4.47.0.dev0",
   "vision_config": {
     "_flash_attn_2_enabled": true,
-    "_attn_implementation": "flash_attention_2",
     "architectures": [
       "AriaVisionModel"
     ],
-    "hidden_size": 1152,
+    "attention_heads": 16,
     "image_size": 980,
     "intermediate_size": 4304,
-    "model_type": "aria_vision_model",
-    "num_attention_heads": 16,
+    "model_type": "idefics3_vision",
     "num_hidden_layers": 27,
     "patch_size": 14,
     "torch_dtype": "bfloat16"
-  }
+  },
+  "vision_feature_layer": -1
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.45.0"
+  "transformers_version": "4.47.0.dev0"
 }

model-00001-of-00012.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f58aac6657c824d7ccbfc590cc1e4dcc25bc361d99837bd92ff5196a2019aaf
-size 4922385968
+oid sha256:07002e78de0e8d6f1142f46dd921929f00c2ff7b7f33558fb0b9142313268d1e
+size 4922385168

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 50614617824
+    "total_size": 50614622432
   },
   "weight_map": {
     "language_model.lm_head.weight": "model-00012-of-00012.safetensors",
@@ -345,455 +345,457 @@
     "multi_modal_projector.cross_attn.k_proj.weight": "model-00001-of-00012.safetensors",
     "multi_modal_projector.cross_attn.layer_norm.bias": "model-00001-of-00012.safetensors",
     "multi_modal_projector.cross_attn.layer_norm.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.layer_norm_kv.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.layer_norm_kv.weight": "model-00001-of-00012.safetensors",
     "multi_modal_projector.cross_attn.linear.bias": "model-00001-of-00012.safetensors",
     "multi_modal_projector.cross_attn.linear.weight": "model-00001-of-00012.safetensors",
-    "multi_modal_projector.cross_attn.ln_kv.bias": "model-00001-of-00012.safetensors",
-    "multi_modal_projector.cross_attn.ln_kv.weight": "model-00001-of-00012.safetensors",
     "multi_modal_projector.cross_attn.multihead_attn.in_proj_bias": "model-00001-of-00012.safetensors",
     "multi_modal_projector.cross_attn.multihead_attn.in_proj_weight": "model-00001-of-00012.safetensors",
     "multi_modal_projector.cross_attn.multihead_attn.out_proj.bias": "model-00001-of-00012.safetensors",
     "multi_modal_projector.cross_attn.multihead_attn.out_proj.weight": "model-00001-of-00012.safetensors",
     "multi_modal_projector.cross_attn.q_proj.weight": "model-00001-of-00012.safetensors",
     "multi_modal_projector.cross_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "multi_modal_projector.ffn.linear_in.weight": "model-00001-of-00012.safetensors",
-    "multi_modal_projector.ffn.linear_out.weight": "model-00001-of-00012.safetensors",
-    "multi_modal_projector.ln_ffn.bias": "model-00001-of-00012.safetensors",
-    "multi_modal_projector.ln_ffn.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.feed_forward.linear_in.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.feed_forward.linear_out.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.layer_norm.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.layer_norm.weight": "model-00001-of-00012.safetensors",
     "multi_modal_projector.query": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00012.safetensors"
+    "vision_tower.embeddings.patch_embedding.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.embeddings.patch_embedding.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.embeddings.position_embedding.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.post_layernorm.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.post_layernorm.weight": "model-00001-of-00012.safetensors"
   }
 }