Upload Blip2ForConditionalGeneration

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:537bb68668d2cc0e84297ee5c23a77e5a86fc28f528afc642155bf5b02dc7e7f
-size 9441197415
+oid sha256:78da3eebf4732877fd22b73dc2ed57dae30c466d5a44b7c329de376fa4c79a88
+size 9441403325

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 16295951872
+    "total_size": 16296171520
   },
   "weight_map": {
     "language_model.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
@@ -834,9 +834,8 @@
     "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.0.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.0.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.0.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.0.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.0.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.0.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -847,9 +846,8 @@
     "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.1.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.1.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.1.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.1.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.1.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.1.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -860,9 +858,8 @@
     "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.10.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.10.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.10.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.10.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.10.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.10.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -873,9 +870,8 @@
     "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.11.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.11.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.11.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.11.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.11.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.11.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -886,9 +882,8 @@
     "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.12.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.12.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.12.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.12.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.12.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.12.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -899,9 +894,8 @@
     "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.13.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.13.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.13.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.13.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.13.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.13.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -912,9 +906,8 @@
     "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.14.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.14.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.14.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.14.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.14.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.14.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -925,9 +918,8 @@
     "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.15.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.15.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.15.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.15.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.15.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.15.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -938,9 +930,8 @@
     "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.16.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.16.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.16.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.16.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.16.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.16.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -951,9 +942,8 @@
     "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.17.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.17.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.17.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.17.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.17.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.17.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -964,9 +954,8 @@
     "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.18.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.18.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.18.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.18.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.18.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.18.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -977,9 +966,8 @@
     "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.19.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.19.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.19.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.19.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.19.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.19.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -990,9 +978,8 @@
     "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.2.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.2.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.2.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.2.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.2.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.2.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1003,9 +990,8 @@
     "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.20.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.20.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.20.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.20.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.20.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.20.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1016,9 +1002,8 @@
     "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.21.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.21.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.21.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.21.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.21.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.21.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1029,9 +1014,8 @@
     "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.22.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.22.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.22.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.22.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.22.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.22.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1042,9 +1026,8 @@
     "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.23.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.23.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.23.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.23.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.23.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.23.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1055,9 +1038,8 @@
     "vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.24.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.24.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.24.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.24.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.24.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.24.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1068,9 +1050,8 @@
     "vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.25.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.25.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.25.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.25.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.25.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.25.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1081,9 +1062,8 @@
     "vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.26.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.26.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.26.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.26.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.26.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.26.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1094,9 +1074,8 @@
     "vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.27.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.27.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.27.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.27.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.27.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.27.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1107,9 +1086,8 @@
     "vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.28.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.28.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.28.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.28.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.28.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.28.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1120,9 +1098,8 @@
     "vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.29.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.29.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.29.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.29.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.29.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.29.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1133,9 +1110,8 @@
     "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.3.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.3.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.3.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.3.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.3.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.3.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1146,9 +1122,8 @@
     "vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.30.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.30.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.30.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.30.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.30.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.30.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1159,9 +1134,8 @@
     "vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.31.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.31.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.31.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.31.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.31.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.31.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.32.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.32.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.32.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1172,9 +1146,8 @@
     "vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.32.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.32.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.32.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.32.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.32.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.32.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.33.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.33.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.33.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1185,9 +1158,8 @@
     "vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.33.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.33.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.33.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.33.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.33.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.33.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.34.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.34.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.34.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1198,9 +1170,8 @@
     "vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.34.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.34.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.34.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.34.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.34.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.34.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.35.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.35.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.35.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1211,9 +1182,8 @@
     "vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.35.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.35.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.35.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.35.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.35.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.35.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.36.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.36.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.36.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1224,9 +1194,8 @@
     "vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.36.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.36.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.36.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.36.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.36.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.36.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.37.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.37.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.37.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1237,9 +1206,8 @@
     "vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.37.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.37.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.37.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.37.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.37.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.37.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.38.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.38.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.38.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1250,9 +1218,8 @@
     "vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.38.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.38.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.38.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.38.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.38.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.38.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1263,9 +1230,8 @@
     "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.4.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.4.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.4.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.4.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.4.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.4.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1276,9 +1242,8 @@
     "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.5.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.5.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.5.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.5.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.5.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.5.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1289,9 +1254,8 @@
     "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.6.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.6.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.6.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.6.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.6.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.6.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1302,9 +1266,8 @@
     "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.7.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.7.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.7.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.7.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.7.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.7.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1315,9 +1278,8 @@
     "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.8.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.8.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.8.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.8.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.8.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.8.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
@@ -1328,9 +1290,8 @@
     "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.9.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.9.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.9.self_attn.q_bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.encoder.layers.9.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.encoder.layers.9.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
-    "vision_model.encoder.layers.9.self_attn.v_bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin"
   }