Upload VLMForCausalLM

config.json

@@ -1,33 +1,95 @@
 {
-  "_attn_implementation_autoset": true,
+  "architectures": [
+    "VLMForCausalLM"
+  ],
   "llm_config": {
     "_name_or_path": "google/gemma-2-2b-it",
     "architectures": [
       "Gemma2ForCausalLM"
     ],
+    "attention_bias": false,
+    "attention_dropout": 0.1,
+    "attn_logit_softcapping": 50.0,
+    "cache_implementation": "hybrid",
     "context_length": 321,
     "eos_token_id": [
       1,
       107
     ],
+    "final_logit_softcapping": 30.0,
+    "head_dim": 256,
     "hidden_act": "gelu_pytorch_tanh",
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2304,
     "image_token": "<image>",
     "image_token_id": 256000,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "max_position_embeddings": 8192,
     "model_type": "gemma2",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 26,
+    "num_key_value_heads": 4,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000.0,
+    "sliding_window": 4096,
     "text_length": 64,
-    "torch_dtype": "float16"
+    "torch_dtype": "float16",
+    "use_cache": true,
+    "vocab_size": 256000
   },
-  "transformers_version": "4.48.3",
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.4",
   "vit_config": {
     "_name_or_path": "facebook/dinov2-base",
+    "apply_layernorm": true,
     "architectures": [
       "Dinov2Model"
     ],
+    "attention_probs_dropout_prob": 0.1,
+    "drop_path_rate": 0.0,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
     "image_size": 518,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-06,
+    "layerscale_value": 1.0,
+    "mlp_ratio": 4,
     "model_type": "dinov2",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
     "num_patches": 257,
     "old_num_patches": 257,
+    "out_features": [
+      "stage12"
+    ],
+    "out_indices": [
+      12
+    ],
+    "patch_size": 14,
+    "qkv_bias": true,
+    "reshape_hidden_states": true,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4",
+      "stage5",
+      "stage6",
+      "stage7",
+      "stage8",
+      "stage9",
+      "stage10",
+      "stage11",
+      "stage12"
+    ],
     "torch_dtype": "float16",
+    "use_mask_token": true,
+    "use_swiglu_ffn": false,
     "visual_embed_dim": 768
   }
 }

generation_config.json

@@ -1,11 +1,4 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 2,
-  "cache_implementation": "hybrid",
-  "eos_token_id": [
-    1,
-    107
-  ],
-  "pad_token_id": 0,
-  "transformers_version": "4.48.3"
+  "transformers_version": "4.52.4"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe04635329d342ca0452c723bd4018d93ccf0fb4598c3a69e6cc47b42c2040f
+size 4966560592

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4441272b5dbffad9d306144a1c57216c32991d4d7383d1cf7860564f7647f162
+size 1618540680

model.safetensors.index.json

@@ -1,520 +1,521 @@
 {
   "metadata": {
-    "total_size": 10810776576
+    "total_size": 6585040896
   },
   "weight_map": {
-    "linear_projector.bias": "model-00003-of-00003.safetensors",
-    "linear_projector.weight": "model-00003-of-00003.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.norm.weight": "model-00003-of-00003.safetensors",
-    "vit.embeddings.cls_token": "model-00003-of-00003.safetensors",
-    "vit.embeddings.mask_token": "model-00003-of-00003.safetensors",
-    "vit.embeddings.patch_embeddings.projection.bias": "model-00003-of-00003.safetensors",
-    "vit.embeddings.patch_embeddings.projection.weight": "model-00003-of-00003.safetensors",
-    "vit.embeddings.position_embeddings": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.0.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.1.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.10.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.11.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.2.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.3.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.4.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.5.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.6.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.7.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.8.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.attention.attention.key.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.attention.attention.key.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.attention.attention.query.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.attention.attention.query.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.attention.attention.value.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.attention.attention.value.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.mlp.fc1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.mlp.fc1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.mlp.fc2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.mlp.fc2.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.norm1.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.norm1.weight": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.norm2.bias": "model-00003-of-00003.safetensors",
-    "vit.encoder.layer.9.norm2.weight": "model-00003-of-00003.safetensors",
-    "vit.layernorm.bias": "model-00003-of-00003.safetensors",
-    "vit.layernorm.weight": "model-00003-of-00003.safetensors"
+    "linear_projector.bias": "model-00001-of-00002.safetensors",
+    "linear_projector.weight": "model-00001-of-00002.safetensors",
+    "llm.lm_head.weight": "model-00002-of-00002.safetensors",
+    "llm.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.norm.weight": "model-00002-of-00002.safetensors",
+    "vit.embeddings.cls_token": "model-00001-of-00002.safetensors",
+    "vit.embeddings.mask_token": "model-00001-of-00002.safetensors",
+    "vit.embeddings.patch_embeddings.projection.bias": "model-00001-of-00002.safetensors",
+    "vit.embeddings.patch_embeddings.projection.weight": "model-00001-of-00002.safetensors",
+    "vit.embeddings.position_embeddings": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.layer_scale1.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.layer_scale2.lambda1": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "vit.encoder.layer.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "vit.layernorm.bias": "model-00001-of-00002.safetensors",
+    "vit.layernorm.weight": "model-00001-of-00002.safetensors"
   }
 }