Upload folder using huggingface_hub

config.json

@@ -147,35 +147,6 @@
     "hidden_activation": "gelu_pytorch_tanh",
     "hidden_size": 1152,
     "intermediate_size": 4304,
-    "layer_types": [
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention"
-    ],
     "max_position_embeddings": 131072,
     "model_type": "gemma4_vision",
     "num_attention_heads": 16,
@@ -186,12 +157,10 @@
     "position_embedding_size": 10240,
     "rms_norm_eps": 1e-06,
     "rope_parameters": {
-      "full_attention": {
-        "rope_theta": 100.0,
-        "rope_type": "default"
-      }
+      "rope_theta": 100.0,
+      "rope_type": "default"
     },
-    "use_bidirectional_attention": "vision",
+    "standardize": true,
     "use_clipped_linears": false
   },
   "vision_soft_tokens_per_image": 280

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a001086872f8e5d237251df64f490f8bf5c3cdc6c29f6cbd16fe1a045a233dcc
-size 49784782228
+oid sha256:dcdca8aebc489295a267a97a1b368d10be542f4b057f19b17bf42341d4b16532
+size 49784788364

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
     "total_parameters": 32682372656,
-    "total_size": 62546173144
+    "total_size": 62546177752
   },
   "weight_map": {
     "model.embed_vision.embedding_projection.weight": "model-00001-of-00002.safetensors",
@@ -838,357 +838,359 @@
     "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.0.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.0.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.0.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.0.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.0.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.0.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.0.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.1.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.1.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.1.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.1.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.1.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.1.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.1.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.10.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.10.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.10.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.10.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.10.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.10.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.10.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.11.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.11.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.11.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.11.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.11.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.11.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.11.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.12.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.12.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.12.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.12.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.12.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.12.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.12.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.13.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.13.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.13.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.13.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.13.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.13.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.13.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.14.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.14.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.14.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.14.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.14.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.14.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.14.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.15.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.15.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.15.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.15.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.15.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.15.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.15.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.16.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.16.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.16.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.16.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.16.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.16.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.16.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.17.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.17.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.17.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.17.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.17.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.17.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.17.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.18.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.18.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.18.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.18.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.18.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.18.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.18.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.19.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.19.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.19.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.19.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.19.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.19.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.19.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.2.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.2.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.2.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.2.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.2.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.2.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.2.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.20.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.20.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.20.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.20.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.20.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.20.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.20.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.21.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.21.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.21.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.21.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.21.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.21.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.21.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.21.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.21.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.22.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.22.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.22.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.22.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.22.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.22.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.22.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.23.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.23.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.23.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.23.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.23.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.23.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.23.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.23.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.23.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.24.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.24.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.24.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.24.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.24.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.24.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.24.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.24.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.24.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.25.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.25.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.25.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.25.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.25.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.25.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.25.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.25.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.25.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.26.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.26.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.26.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.26.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.26.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.26.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.26.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.26.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.26.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.3.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.3.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.3.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.3.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.3.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.3.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.3.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.4.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.4.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.4.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.4.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.4.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.4.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.4.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.5.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.5.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.5.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.5.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.5.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.5.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.5.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.6.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.6.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.6.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.6.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.6.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.6.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.6.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.7.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.7.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.7.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.7.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.7.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.7.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.7.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.8.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.8.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.8.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.8.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.8.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.8.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.8.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.9.mlp.down_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.9.mlp.gate_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.9.mlp.up_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.9.self_attn.k_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.9.self_attn.o_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.encoder.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.9.self_attn.q_proj.linear.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.encoder.layers.9.self_attn.v_proj.linear.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.patch_embedder.input_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.patch_embedder.position_embedding_table": "model-00001-of-00002.safetensors"
+    "model.vision_tower.patch_embedder.position_embedding_table": "model-00001-of-00002.safetensors",
+    "model.vision_tower.std_bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.std_scale": "model-00001-of-00002.safetensors"
   }
 }

processor_config.json

@@ -28,26 +28,22 @@
     "do_rescale": true,
     "do_resize": true,
     "image_mean": [
-      0.5,
-      0.5,
-      0.5
+      0.0,
+      0.0,
+      0.0
     ],
     "image_processor_type": "Gemma4ImageProcessor",
     "image_seq_length": 280,
     "image_std": [
-      0.5,
-      0.5,
-      0.5
+      1.0,
+      1.0,
+      1.0
     ],
     "max_soft_tokens": 280,
     "patch_size": 16,
     "pooling_kernel_size": 3,
     "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "size": {
-      "height": 224,
-      "width": 224
-    }
+    "rescale_factor": 0.00392156862745098
   },
   "image_seq_length": 280,
   "processor_class": "Gemma4Processor"