Upload folder using huggingface_hub

README.md

@@ -1,12 +1,4 @@
 ---
-language:
-- en
-license: apache-2.0
-tags:
-- multimodal
-- vision
-- image-text-to-text
-- mlx
 datasets:
 - HuggingFaceM4/OBELICS
 - laion/laion-coco
@@ -25,10 +17,20 @@ datasets:
 - camel-ai/math
 - AtlasUnified/atlas-math-sets
 - tiedong/goat
+- Lin-Chen/ShareGPT4V
+- jxu124/llava_conversation_58k
+language:
+- en
+license: apache-2.0
+tags:
+- multimodal
+- vision
+- image-text-to-text
+- mlx
 ---
 
 # mlx-community/idefics2-8b-8bit
-This model was converted to MLX format from [`HuggingFaceM4/idefics2-8b`]() using mlx-vlm version **0.0.4**.
+This model was converted to MLX format from [`HuggingFaceM4/idefics2-8b`]() using mlx-vlm version **0.1.0**.
 Refer to the [original model card](https://huggingface.co/HuggingFaceM4/idefics2-8b) for more details on the model.
 ## Use with mlx
 

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
+}

config.json

@@ -25,7 +25,7 @@
     "vision_config": {
         "hidden_size": 1152,
         "image_size": 980,
-        "intermediate_size": 4304,
+        "intermediate_size": 4352,
         "model_type": "idefics2",
         "num_attention_heads": 16,
         "num_hidden_layers": 27,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be8c0e81e3a86c808ab25ae143f7d0cb28adfcefe1d3e70ae54dd5aa9ad4f79
-size 5313954350
+oid sha256:34c68c02f44828f54b3f2af3d839a689c3d54bf1395c738d521ae66f1d9bf02f
+size 5346726218

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dae6e019c163b348a6839e9167d4b74d6c707f3b9272218839e829ac1782298
-size 4129248613
+oid sha256:5056a42c867177102819de30c4a07f753d1de0f651d0f31f4ed2b898cd346a7c
+size 3603348985

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
     "metadata": {
-        "total_size": 9443046624
+        "total_size": 8949877536
     },
     "weight_map": {
         "connector.modality_projection.down_proj.biases": "model-00002-of-00002.safetensors",
@@ -86,6 +86,8 @@
         "connector.perceiver_resampler.layers.2.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
         "connector.perceiver_resampler.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
         "connector.perceiver_resampler.norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+        "language_model.embed_tokens.scales": "model-00001-of-00002.safetensors",
         "language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
         "language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
         "language_model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
@@ -317,17 +319,17 @@
         "language_model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
         "language_model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.18.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.18.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.18.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.18.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.18.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.18.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
         "language_model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
         "language_model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
@@ -340,29 +342,29 @@
         "language_model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
         "language_model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
         "language_model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
         "language_model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
@@ -390,25 +392,25 @@
         "language_model.layers.20.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
         "language_model.layers.20.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
         "language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
         "language_model.layers.20.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
         "language_model.layers.20.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
         "language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
         "language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
         "language_model.layers.21.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
         "language_model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
@@ -829,438 +831,764 @@
         "language_model.norm.weight": "model-00002-of-00002.safetensors",
         "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
         "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
+        "vision_model.embeddings.position_embedding.biases": "model-00001-of-00002.safetensors",
+        "vision_model.embeddings.position_embedding.scales": "model-00001-of-00002.safetensors",
         "vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc1.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc1.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc2.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc2.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "vision_model.encoder.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
         "vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
         "vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
         "vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"

preprocessor_config.json

@@ -1,6 +1,6 @@
 {
   "do_convert_rgb": true,
-  "do_image_splitting": false,
+  "do_image_splitting": true,
   "do_normalize": true,
   "do_pad": true,
   "do_rescale": true,

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -59,6 +60,7 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<unk>",
   "processor_class": "Idefics2Processor",