Upload Blip2ForConditionalGeneration

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4b98a2d25e82aa974213e0692d3b3c9eacb661697ab5e266de36b4814d50f0
-size 9998401875
+oid sha256:12f6dd9768543377854c52b46d5d2da70de1556631791977c8ceb4b9a59cff2a
+size 9998605244

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 15495650816
+    "total_size": 15495870464
   },
   "weight_map": {
     "language_model.lm_head.weight": "pytorch_model-00002-of-00002.bin",
@@ -791,9 +791,8 @@
     "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",
@@ -804,9 +803,8 @@
     "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",
@@ -817,9 +815,8 @@
     "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",
@@ -830,9 +827,8 @@
     "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",
@@ -843,9 +839,8 @@
     "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",
@@ -856,9 +851,8 @@
     "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",
@@ -869,9 +863,8 @@
     "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",
@@ -882,9 +875,8 @@
     "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",
@@ -895,9 +887,8 @@
     "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",
@@ -908,9 +899,8 @@
     "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",
@@ -921,9 +911,8 @@
     "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",
@@ -934,9 +923,8 @@
     "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",
@@ -947,9 +935,8 @@
     "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",
@@ -960,9 +947,8 @@
     "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",
@@ -973,9 +959,8 @@
     "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",
@@ -986,9 +971,8 @@
     "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",
@@ -999,9 +983,8 @@
     "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",
@@ -1012,9 +995,8 @@
     "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",
@@ -1025,9 +1007,8 @@
     "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",
@@ -1038,9 +1019,8 @@
     "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",
@@ -1051,9 +1031,8 @@
     "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",
@@ -1064,9 +1043,8 @@
     "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",
@@ -1077,9 +1055,8 @@
     "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",
@@ -1090,9 +1067,8 @@
     "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",
@@ -1103,9 +1079,8 @@
     "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",
@@ -1116,9 +1091,8 @@
     "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",
@@ -1129,9 +1103,8 @@
     "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",
@@ -1142,9 +1115,8 @@
     "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",
@@ -1155,9 +1127,8 @@
     "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",
@@ -1168,9 +1139,8 @@
     "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",
@@ -1181,9 +1151,8 @@
     "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",
@@ -1194,9 +1163,8 @@
     "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",
@@ -1207,9 +1175,8 @@
     "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",
@@ -1220,9 +1187,8 @@
     "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",
@@ -1233,9 +1199,8 @@
     "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",
@@ -1246,9 +1211,8 @@
     "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",
@@ -1259,9 +1223,8 @@
     "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",
@@ -1272,9 +1235,8 @@
     "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",
@@ -1285,9 +1247,8 @@
     "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"
   }