Upload JanusForConditionalGeneration

config.json

@@ -1,4 +1,7 @@
 {
+  "architectures": [
+    "JanusForConditionalGeneration"
+  ],
   "image_token_index": 100594,
   "model_type": "janus",
   "text_config": {
@@ -26,6 +29,7 @@
     "use_cache": true,
     "vocab_size": 102400
   },
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.52.0.dev0",
   "vision_config": {
     "attention_bias": true,

generation_config.json

@@ -2,7 +2,10 @@
   "_from_model_config": true,
   "bos_token_id": 100000,
   "eos_token_id": 100001,
+  "generation_kwargs": {
+    "boi_token_id": 100016
+  },
   "guidance_scale": 5,
   "pad_token_id": 100015,
-  "transformers_version": "4.50.0.dev0"
+  "transformers_version": "4.52.0.dev0"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b323162924d4d4c6fdb79d8ed19c383d4f22033e8bab0d15be283df56bc1343
-size 4916719910
+oid sha256:c75c3abf946ba6f523fa8ea3b30fb0e15cd11438677c291b277cf93eb1ca9d00
+size 4981719342

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be091e603eb2f4f6fd8fe7dbb8d609f09286ae705ecc176d3d786642cad5c20c
-size 4947392496
+oid sha256:5bccb41fbf819986c359905b5227b4476d9bfe838862499a3f987030b72eeca5
+size 4980963712

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8ab7f0291d4c1e600d59409c55fb10c051c2a545cc1a7314fd3140017b7318e
-size 4976742592
+oid sha256:7480680b7def008b29bca684c7c36bba3d3f47d2b585ed1a35faf15156f7c8ed
+size 4852993720

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14840737046
+    "total_size": 14815546646
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -8,15 +8,15 @@
     "model.aligner.fc1.weight": "model-00001-of-00003.safetensors",
     "model.aligner.hidden_layers.0.bias": "model-00001-of-00003.safetensors",
     "model.aligner.hidden_layers.0.weight": "model-00001-of-00003.safetensors",
-    "model.gen_aligner.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.gen_aligner.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.gen_aligner.hidden_layers.0.bias": "model-00001-of-00003.safetensors",
-    "model.gen_aligner.hidden_layers.0.weight": "model-00001-of-00003.safetensors",
-    "model.gen_embed.weight": "model-00001-of-00003.safetensors",
-    "model.gen_head.proj_out.bias": "model-00001-of-00003.safetensors",
-    "model.gen_head.proj_out.weight": "model-00001-of-00003.safetensors",
-    "model.gen_head.vision_head.bias": "model-00001-of-00003.safetensors",
-    "model.gen_head.vision_head.weight": "model-00001-of-00003.safetensors",
+    "model.generation_aligner.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.generation_aligner.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.generation_aligner.hidden_layers.0.bias": "model-00001-of-00003.safetensors",
+    "model.generation_aligner.hidden_layers.0.weight": "model-00001-of-00003.safetensors",
+    "model.generation_embeddings.weight": "model-00001-of-00003.safetensors",
+    "model.generation_head.proj_out.bias": "model-00001-of-00003.safetensors",
+    "model.generation_head.proj_out.weight": "model-00001-of-00003.safetensors",
+    "model.generation_head.vision_head.bias": "model-00001-of-00003.safetensors",
+    "model.generation_head.vision_head.weight": "model-00001-of-00003.safetensors",
     "model.language_model.embed_tokens.weight": "model-00001-of-00003.safetensors",
     "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
@@ -117,11 +117,11 @@
     "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
@@ -142,7 +142,7 @@
     "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -264,7 +264,7 @@
     "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -289,13 +289,9 @@
     "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.language_model.norm.weight": "model-00003-of-00003.safetensors",
-    "model.vision_model.embeddings.patch_embeddings.projection.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.embeddings.patch_embeddings.projection.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.embeddings.position_embeddings.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.0.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.0.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -304,10 +300,14 @@
     "model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.1.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.1.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -316,10 +316,14 @@
     "model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.10.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.10.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -328,10 +332,14 @@
     "model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.11.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.11.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -340,10 +348,14 @@
     "model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.12.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.12.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -352,10 +364,14 @@
     "model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.13.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.13.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -364,10 +380,14 @@
     "model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.14.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.14.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -376,10 +396,14 @@
     "model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.15.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.15.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -388,10 +412,14 @@
     "model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.16.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.16.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -400,10 +428,14 @@
     "model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.17.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.17.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -412,10 +444,14 @@
     "model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.18.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.18.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -424,10 +460,14 @@
     "model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.19.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.19.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -436,10 +476,14 @@
     "model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.2.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.2.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -448,10 +492,14 @@
     "model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.20.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.20.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -460,10 +508,14 @@
     "model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.21.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.21.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -472,10 +524,14 @@
     "model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.22.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.22.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -484,10 +540,14 @@
     "model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.23.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.23.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -496,10 +556,14 @@
     "model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.3.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.3.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -508,10 +572,14 @@
     "model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.4.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.4.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -520,10 +588,14 @@
     "model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.5.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.5.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -532,10 +604,14 @@
     "model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.6.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.6.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -544,10 +620,14 @@
     "model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.7.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.7.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -556,10 +636,14 @@
     "model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.8.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.8.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -568,10 +652,14 @@
     "model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.9.attn.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.9.attn.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00003.safetensors",
@@ -580,19 +668,14 @@
     "model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.kv.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.kv.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.latent": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.layer_norm.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.layer_norm.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.projection_layer.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.projection_layer.weight": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.q.bias": "model-00001-of-00003.safetensors",
-    "model.vision_model.head.q.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.projection_layer.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.projection_layer.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.vision_model.post_layernorm.bias": "model-00001-of-00003.safetensors",
     "model.vision_model.post_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.vqmodel.decoder.conv_in.bias": "model-00001-of-00003.safetensors",