Upload folder using huggingface_hub

README.md

@@ -6,6 +6,10 @@ base_model:
 license: apache-2.0
 pipeline_tag: image-text-to-text
 ---
+> [!NOTE]
+>  Includes Unsloth **chat template fixes**! <br> For `llama.cpp`, use `--jinja`
+>
+
 <div>
 <p style="margin-top: 0;margin-bottom: 0;">
     <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>

config.json

@@ -2,8 +2,6 @@
   "architectures": [
     "Qwen3VLForConditionalGeneration"
   ],
-  "torch_dtype": "bfloat16",
-  "eos_token_id": 151645,
   "image_token_id": 151655,
   "model_type": "qwen3_vl",
   "pad_token_id": 151654,
@@ -48,7 +46,6 @@
       24
     ],
     "depth": 27,
-    "torch_dtype": "bfloat16",
     "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 1152,
     "in_channels": 3,
@@ -64,4 +61,4 @@
   },
   "vision_end_token_id": 151653,
   "vision_start_token_id": 151652
-}
+}

generation_config.json

@@ -1,12 +1,14 @@
 {
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151654,
-  "top_k": 20,
-  "top_p": 0.95,
-  "transformers_version": "4.57.1"
-}
+    "bos_token_id": 151643,
+    "pad_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "top_k": 20,
+    "top_p": 0.95,
+    "repetition_penalty": 1.0,
+    "temperature": 1.0,
+    "transformers_version": "4.56.0"
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4051d3f9ad577bc598c634140eda26244bb475a714806f9c0f2df843d7f0fe17
-size 4998056552
+oid sha256:9a2ad68570fe788a0bbf03ed07c1d32cea83884fa328c587a5ef97d797cf2e91
+size 4902275944

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b31a39ddd7d9e6c94361e737446612f060af55899e08d4594cf754578c1e23d
-size 4915962464
+oid sha256:5192d62fbc367626d743551b6a91461bfae305db6cf71eaeade89598d21e4f7d
+size 4915962496

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bf66e8b43a4f52c1088a28b0d8b63b2f4968d39c31060204f7780674617a19
-size 4915962496
+oid sha256:4931c8b5e85666292daa65153726b20030f54d81d8f51d732a367b9e051e5fbc
+size 4999831048

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9996a35fcad41eb1998c94328bd703152fb0053a4a2124cb1c5fe7e1efa18929
-size 2704357976
+oid sha256:ef14a367ae345934318ea7b06bf404b97c3a312418f40dd5f92d8296af96de13
+size 2716270024

model.safetensors.index.json

@@ -1,6 +1,5 @@
 {
   "metadata": {
-    "total_parameters": 8767123696,
     "total_size": 17534247392
   },
   "weight_map": {
@@ -127,11 +126,11 @@
     "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
     "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
@@ -149,39 +148,39 @@
     "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -292,39 +291,39 @@
     "model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
@@ -332,9 +331,9 @@
     "model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
@@ -358,401 +357,401 @@
     "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
-    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
-    "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
-    "model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
-    "model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
-    "model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
-    "model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
-    "model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
-    "model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
-    "model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
-    "model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
-    "model.visual.pos_embed.weight": "model-00001-of-00004.safetensors"
+    "model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00004-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
+    "model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
   }
 }