Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image>": 257152
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "PaliGemmaForConditionalGeneration"
+  ],
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "hidden_size": 2048,
+  "ignore_index": -100,
+  "image_token_index": 257152,
+  "model_type": "paligemma",
+  "pad_token_id": 0,
+  "projection_dim": 2048,
+  "text_config": {
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2048,
+    "intermediate_size": 16384,
+    "model_type": "gemma",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 18,
+    "num_image_tokens": 256,
+    "num_key_value_heads": 1,
+    "torch_dtype": "float16",
+    "vocab_size": 257216
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "vision_config": {
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "num_image_tokens": 256,
+    "patch_size": 14,
+    "projection_dim": 2048,
+    "projector_hidden_act": "gelu_fast",
+    "torch_dtype": "float16",
+    "vision_use_head": false
+  },
+  "vocab_size": 257216
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.0.dev0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ef92efc02422e42ca6112f83df8aba61621c7f9fd58ab9eebcc22f730b0bab
+size 2107113624

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bdb2f18a0aea42077265e9a0fc7b3549c2932f512aab7de245bf074e72b993f
+size 1965459568

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9fc966c392a69f486931241d37f3350f9daf8a8094a6ae7ed881b4aeebed4f
+size 1933661624

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4d4e0ac159dad08ceba494e34474e199b2071d10626d953553db3f93f9cbe3
+size 1895895728

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df59e5a75b9a7ccd0c54584dda9151cac3693d5d5472a155edb646a659428098
+size 1895895752

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7268254ba0fae9e68ba116699a183b4b5727fce72ea31ef79f94207e1a0083ea
+size 1895920704

model.safetensors.index.json

@@ -0,0 +1,610 @@
+{
+  "metadata": {
+    "total_size": 11693865920
+  },
+  "weight_map": {
+    "language_model.model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.norm.weight": "model-00006-of-00006.safetensors",
+    "multi_modal_projector.linear.bias": "model-00002-of-00006.safetensors",
+    "multi_modal_projector.linear.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00006.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,40 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format",
+    "do_convert_rgb"
+  ],
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "PaliGemmaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8104de0e0f9b8ab923ac66b31bee4ae132edf05863545fa4a3b69b4774117ae
+size 17763304

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8986bb4f423f07f8c7f70d0dbe3526fb2316056c17bae71b1ea975e77a168fc6
+size 4264023