nielsr HF staff commited on
Commit
719129e
1 Parent(s): 4729e53

Upload Blip2ForConditionalGeneration

Browse files
pytorch_model-00001-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d76d3bfcab9f4afe4555dd70af78a6627462ebc74e0637170b3122d85ffc5695
3
- size 9799060633
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59da5daee91fcd831942842bc1bf7a6b9d92866d7c2ecf1e210595bfb7c664d
3
+ size 9799266532
pytorch_model.bin.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 31834390016
4
  },
5
  "weight_map": {
6
  "language_model.lm_head.weight": "pytorch_model-00004-of-00004.bin",
@@ -791,9 +791,8 @@
791
  "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
792
  "vision_model.encoder.layers.0.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
793
  "vision_model.encoder.layers.0.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
794
- "vision_model.encoder.layers.0.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
795
  "vision_model.encoder.layers.0.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
796
- "vision_model.encoder.layers.0.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
797
  "vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
798
  "vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
799
  "vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -804,9 +803,8 @@
804
  "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
805
  "vision_model.encoder.layers.1.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
806
  "vision_model.encoder.layers.1.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
807
- "vision_model.encoder.layers.1.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
808
  "vision_model.encoder.layers.1.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
809
- "vision_model.encoder.layers.1.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
810
  "vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
811
  "vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
812
  "vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -817,9 +815,8 @@
817
  "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
818
  "vision_model.encoder.layers.10.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
819
  "vision_model.encoder.layers.10.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
820
- "vision_model.encoder.layers.10.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
821
  "vision_model.encoder.layers.10.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
822
- "vision_model.encoder.layers.10.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
823
  "vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
824
  "vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
825
  "vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -830,9 +827,8 @@
830
  "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
831
  "vision_model.encoder.layers.11.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
832
  "vision_model.encoder.layers.11.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
833
- "vision_model.encoder.layers.11.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
834
  "vision_model.encoder.layers.11.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
835
- "vision_model.encoder.layers.11.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
836
  "vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
837
  "vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
838
  "vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -843,9 +839,8 @@
843
  "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
844
  "vision_model.encoder.layers.12.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
845
  "vision_model.encoder.layers.12.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
846
- "vision_model.encoder.layers.12.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
847
  "vision_model.encoder.layers.12.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
848
- "vision_model.encoder.layers.12.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
849
  "vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
850
  "vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
851
  "vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -856,9 +851,8 @@
856
  "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
857
  "vision_model.encoder.layers.13.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
858
  "vision_model.encoder.layers.13.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
859
- "vision_model.encoder.layers.13.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
860
  "vision_model.encoder.layers.13.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
861
- "vision_model.encoder.layers.13.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
862
  "vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
863
  "vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
864
  "vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -869,9 +863,8 @@
869
  "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
870
  "vision_model.encoder.layers.14.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
871
  "vision_model.encoder.layers.14.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
872
- "vision_model.encoder.layers.14.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
873
  "vision_model.encoder.layers.14.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
874
- "vision_model.encoder.layers.14.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
875
  "vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
876
  "vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
877
  "vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -882,9 +875,8 @@
882
  "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
883
  "vision_model.encoder.layers.15.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
884
  "vision_model.encoder.layers.15.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
885
- "vision_model.encoder.layers.15.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
886
  "vision_model.encoder.layers.15.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
887
- "vision_model.encoder.layers.15.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
888
  "vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
889
  "vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
890
  "vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -895,9 +887,8 @@
895
  "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
896
  "vision_model.encoder.layers.16.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
897
  "vision_model.encoder.layers.16.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
898
- "vision_model.encoder.layers.16.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
899
  "vision_model.encoder.layers.16.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
900
- "vision_model.encoder.layers.16.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
901
  "vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
902
  "vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
903
  "vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -908,9 +899,8 @@
908
  "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
909
  "vision_model.encoder.layers.17.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
910
  "vision_model.encoder.layers.17.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
911
- "vision_model.encoder.layers.17.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
912
  "vision_model.encoder.layers.17.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
913
- "vision_model.encoder.layers.17.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
914
  "vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
915
  "vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
916
  "vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -921,9 +911,8 @@
921
  "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
922
  "vision_model.encoder.layers.18.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
923
  "vision_model.encoder.layers.18.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
924
- "vision_model.encoder.layers.18.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
925
  "vision_model.encoder.layers.18.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
926
- "vision_model.encoder.layers.18.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
927
  "vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
928
  "vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
929
  "vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -934,9 +923,8 @@
934
  "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
935
  "vision_model.encoder.layers.19.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
936
  "vision_model.encoder.layers.19.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
937
- "vision_model.encoder.layers.19.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
938
  "vision_model.encoder.layers.19.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
939
- "vision_model.encoder.layers.19.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
940
  "vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
941
  "vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
942
  "vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -947,9 +935,8 @@
947
  "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
948
  "vision_model.encoder.layers.2.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
949
  "vision_model.encoder.layers.2.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
950
- "vision_model.encoder.layers.2.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
951
  "vision_model.encoder.layers.2.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
952
- "vision_model.encoder.layers.2.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
953
  "vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
954
  "vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
955
  "vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -960,9 +947,8 @@
960
  "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
961
  "vision_model.encoder.layers.20.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
962
  "vision_model.encoder.layers.20.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
963
- "vision_model.encoder.layers.20.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
964
  "vision_model.encoder.layers.20.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
965
- "vision_model.encoder.layers.20.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
966
  "vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
967
  "vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
968
  "vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -973,9 +959,8 @@
973
  "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
974
  "vision_model.encoder.layers.21.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
975
  "vision_model.encoder.layers.21.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
976
- "vision_model.encoder.layers.21.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
977
  "vision_model.encoder.layers.21.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
978
- "vision_model.encoder.layers.21.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
979
  "vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
980
  "vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
981
  "vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -986,9 +971,8 @@
986
  "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
987
  "vision_model.encoder.layers.22.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
988
  "vision_model.encoder.layers.22.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
989
- "vision_model.encoder.layers.22.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
990
  "vision_model.encoder.layers.22.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
991
- "vision_model.encoder.layers.22.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
992
  "vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
993
  "vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
994
  "vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -999,9 +983,8 @@
999
  "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1000
  "vision_model.encoder.layers.23.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1001
  "vision_model.encoder.layers.23.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1002
- "vision_model.encoder.layers.23.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1003
  "vision_model.encoder.layers.23.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1004
- "vision_model.encoder.layers.23.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1005
  "vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1006
  "vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1007
  "vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1012,9 +995,8 @@
1012
  "vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1013
  "vision_model.encoder.layers.24.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1014
  "vision_model.encoder.layers.24.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1015
- "vision_model.encoder.layers.24.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1016
  "vision_model.encoder.layers.24.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1017
- "vision_model.encoder.layers.24.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1018
  "vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1019
  "vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1020
  "vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1025,9 +1007,8 @@
1025
  "vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1026
  "vision_model.encoder.layers.25.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1027
  "vision_model.encoder.layers.25.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1028
- "vision_model.encoder.layers.25.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1029
  "vision_model.encoder.layers.25.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1030
- "vision_model.encoder.layers.25.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1031
  "vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1032
  "vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1033
  "vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1038,9 +1019,8 @@
1038
  "vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1039
  "vision_model.encoder.layers.26.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1040
  "vision_model.encoder.layers.26.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1041
- "vision_model.encoder.layers.26.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1042
  "vision_model.encoder.layers.26.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1043
- "vision_model.encoder.layers.26.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1044
  "vision_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1045
  "vision_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1046
  "vision_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1051,9 +1031,8 @@
1051
  "vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1052
  "vision_model.encoder.layers.27.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1053
  "vision_model.encoder.layers.27.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1054
- "vision_model.encoder.layers.27.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1055
  "vision_model.encoder.layers.27.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1056
- "vision_model.encoder.layers.27.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1057
  "vision_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1058
  "vision_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1059
  "vision_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1064,9 +1043,8 @@
1064
  "vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1065
  "vision_model.encoder.layers.28.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1066
  "vision_model.encoder.layers.28.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1067
- "vision_model.encoder.layers.28.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1068
  "vision_model.encoder.layers.28.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1069
- "vision_model.encoder.layers.28.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1070
  "vision_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1071
  "vision_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1072
  "vision_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1077,9 +1055,8 @@
1077
  "vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1078
  "vision_model.encoder.layers.29.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1079
  "vision_model.encoder.layers.29.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1080
- "vision_model.encoder.layers.29.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1081
  "vision_model.encoder.layers.29.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1082
- "vision_model.encoder.layers.29.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1083
  "vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1084
  "vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1085
  "vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1090,9 +1067,8 @@
1090
  "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1091
  "vision_model.encoder.layers.3.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1092
  "vision_model.encoder.layers.3.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1093
- "vision_model.encoder.layers.3.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1094
  "vision_model.encoder.layers.3.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1095
- "vision_model.encoder.layers.3.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1096
  "vision_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1097
  "vision_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1098
  "vision_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1103,9 +1079,8 @@
1103
  "vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1104
  "vision_model.encoder.layers.30.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1105
  "vision_model.encoder.layers.30.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1106
- "vision_model.encoder.layers.30.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1107
  "vision_model.encoder.layers.30.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1108
- "vision_model.encoder.layers.30.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1109
  "vision_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1110
  "vision_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1111
  "vision_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1116,9 +1091,8 @@
1116
  "vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1117
  "vision_model.encoder.layers.31.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1118
  "vision_model.encoder.layers.31.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1119
- "vision_model.encoder.layers.31.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1120
  "vision_model.encoder.layers.31.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1121
- "vision_model.encoder.layers.31.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1122
  "vision_model.encoder.layers.32.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1123
  "vision_model.encoder.layers.32.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1124
  "vision_model.encoder.layers.32.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1129,9 +1103,8 @@
1129
  "vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1130
  "vision_model.encoder.layers.32.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1131
  "vision_model.encoder.layers.32.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1132
- "vision_model.encoder.layers.32.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1133
  "vision_model.encoder.layers.32.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1134
- "vision_model.encoder.layers.32.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1135
  "vision_model.encoder.layers.33.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1136
  "vision_model.encoder.layers.33.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1137
  "vision_model.encoder.layers.33.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1142,9 +1115,8 @@
1142
  "vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1143
  "vision_model.encoder.layers.33.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1144
  "vision_model.encoder.layers.33.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1145
- "vision_model.encoder.layers.33.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1146
  "vision_model.encoder.layers.33.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1147
- "vision_model.encoder.layers.33.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1148
  "vision_model.encoder.layers.34.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1149
  "vision_model.encoder.layers.34.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1150
  "vision_model.encoder.layers.34.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1155,9 +1127,8 @@
1155
  "vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1156
  "vision_model.encoder.layers.34.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1157
  "vision_model.encoder.layers.34.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1158
- "vision_model.encoder.layers.34.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1159
  "vision_model.encoder.layers.34.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1160
- "vision_model.encoder.layers.34.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1161
  "vision_model.encoder.layers.35.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1162
  "vision_model.encoder.layers.35.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1163
  "vision_model.encoder.layers.35.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1168,9 +1139,8 @@
1168
  "vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1169
  "vision_model.encoder.layers.35.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1170
  "vision_model.encoder.layers.35.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1171
- "vision_model.encoder.layers.35.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1172
  "vision_model.encoder.layers.35.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1173
- "vision_model.encoder.layers.35.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1174
  "vision_model.encoder.layers.36.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1175
  "vision_model.encoder.layers.36.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1176
  "vision_model.encoder.layers.36.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1181,9 +1151,8 @@
1181
  "vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1182
  "vision_model.encoder.layers.36.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1183
  "vision_model.encoder.layers.36.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1184
- "vision_model.encoder.layers.36.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1185
  "vision_model.encoder.layers.36.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1186
- "vision_model.encoder.layers.36.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1187
  "vision_model.encoder.layers.37.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1188
  "vision_model.encoder.layers.37.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1189
  "vision_model.encoder.layers.37.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1194,9 +1163,8 @@
1194
  "vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1195
  "vision_model.encoder.layers.37.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1196
  "vision_model.encoder.layers.37.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1197
- "vision_model.encoder.layers.37.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1198
  "vision_model.encoder.layers.37.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1199
- "vision_model.encoder.layers.37.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1200
  "vision_model.encoder.layers.38.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1201
  "vision_model.encoder.layers.38.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1202
  "vision_model.encoder.layers.38.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1207,9 +1175,8 @@
1207
  "vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1208
  "vision_model.encoder.layers.38.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1209
  "vision_model.encoder.layers.38.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1210
- "vision_model.encoder.layers.38.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1211
  "vision_model.encoder.layers.38.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1212
- "vision_model.encoder.layers.38.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1213
  "vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1214
  "vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1215
  "vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1220,9 +1187,8 @@
1220
  "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1221
  "vision_model.encoder.layers.4.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1222
  "vision_model.encoder.layers.4.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1223
- "vision_model.encoder.layers.4.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1224
  "vision_model.encoder.layers.4.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1225
- "vision_model.encoder.layers.4.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1226
  "vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1227
  "vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1228
  "vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1233,9 +1199,8 @@
1233
  "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1234
  "vision_model.encoder.layers.5.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1235
  "vision_model.encoder.layers.5.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1236
- "vision_model.encoder.layers.5.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1237
  "vision_model.encoder.layers.5.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1238
- "vision_model.encoder.layers.5.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1239
  "vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1240
  "vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1241
  "vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1246,9 +1211,8 @@
1246
  "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1247
  "vision_model.encoder.layers.6.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1248
  "vision_model.encoder.layers.6.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1249
- "vision_model.encoder.layers.6.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1250
  "vision_model.encoder.layers.6.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1251
- "vision_model.encoder.layers.6.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1252
  "vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1253
  "vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1254
  "vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1259,9 +1223,8 @@
1259
  "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1260
  "vision_model.encoder.layers.7.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1261
  "vision_model.encoder.layers.7.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1262
- "vision_model.encoder.layers.7.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1263
  "vision_model.encoder.layers.7.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1264
- "vision_model.encoder.layers.7.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1265
  "vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1266
  "vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1267
  "vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1272,9 +1235,8 @@
1272
  "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1273
  "vision_model.encoder.layers.8.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1274
  "vision_model.encoder.layers.8.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1275
- "vision_model.encoder.layers.8.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1276
  "vision_model.encoder.layers.8.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1277
- "vision_model.encoder.layers.8.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1278
  "vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1279
  "vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1280
  "vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
@@ -1285,9 +1247,8 @@
1285
  "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1286
  "vision_model.encoder.layers.9.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1287
  "vision_model.encoder.layers.9.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1288
- "vision_model.encoder.layers.9.self_attn.q_bias": "pytorch_model-00001-of-00004.bin",
1289
  "vision_model.encoder.layers.9.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
1290
- "vision_model.encoder.layers.9.self_attn.v_bias": "pytorch_model-00001-of-00004.bin",
1291
  "vision_model.post_layernorm.bias": "pytorch_model-00001-of-00004.bin",
1292
  "vision_model.post_layernorm.weight": "pytorch_model-00001-of-00004.bin"
1293
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 31834609664
4
  },
5
  "weight_map": {
6
  "language_model.lm_head.weight": "pytorch_model-00004-of-00004.bin",
 
791
  "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
792
  "vision_model.encoder.layers.0.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
793
  "vision_model.encoder.layers.0.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
794
+ "vision_model.encoder.layers.0.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
795
  "vision_model.encoder.layers.0.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
796
  "vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
797
  "vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
798
  "vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
803
  "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
804
  "vision_model.encoder.layers.1.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
805
  "vision_model.encoder.layers.1.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
806
+ "vision_model.encoder.layers.1.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
807
  "vision_model.encoder.layers.1.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
808
  "vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
809
  "vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
810
  "vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
815
  "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
816
  "vision_model.encoder.layers.10.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
817
  "vision_model.encoder.layers.10.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
818
+ "vision_model.encoder.layers.10.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
819
  "vision_model.encoder.layers.10.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
820
  "vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
821
  "vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
822
  "vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
827
  "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
828
  "vision_model.encoder.layers.11.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
829
  "vision_model.encoder.layers.11.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
830
+ "vision_model.encoder.layers.11.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
831
  "vision_model.encoder.layers.11.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
832
  "vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
833
  "vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
834
  "vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
839
  "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
840
  "vision_model.encoder.layers.12.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
841
  "vision_model.encoder.layers.12.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
842
+ "vision_model.encoder.layers.12.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
843
  "vision_model.encoder.layers.12.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
844
  "vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
845
  "vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
846
  "vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
851
  "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
852
  "vision_model.encoder.layers.13.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
853
  "vision_model.encoder.layers.13.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
854
+ "vision_model.encoder.layers.13.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
855
  "vision_model.encoder.layers.13.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
856
  "vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
857
  "vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
858
  "vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
863
  "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
864
  "vision_model.encoder.layers.14.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
865
  "vision_model.encoder.layers.14.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
866
+ "vision_model.encoder.layers.14.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
867
  "vision_model.encoder.layers.14.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
868
  "vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
869
  "vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
870
  "vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
875
  "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
876
  "vision_model.encoder.layers.15.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
877
  "vision_model.encoder.layers.15.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
878
+ "vision_model.encoder.layers.15.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
879
  "vision_model.encoder.layers.15.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
880
  "vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
881
  "vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
882
  "vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
887
  "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
888
  "vision_model.encoder.layers.16.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
889
  "vision_model.encoder.layers.16.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
890
+ "vision_model.encoder.layers.16.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
891
  "vision_model.encoder.layers.16.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
892
  "vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
893
  "vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
894
  "vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
899
  "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
900
  "vision_model.encoder.layers.17.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
901
  "vision_model.encoder.layers.17.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
902
+ "vision_model.encoder.layers.17.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
903
  "vision_model.encoder.layers.17.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
904
  "vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
905
  "vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
906
  "vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
911
  "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
912
  "vision_model.encoder.layers.18.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
913
  "vision_model.encoder.layers.18.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
914
+ "vision_model.encoder.layers.18.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
915
  "vision_model.encoder.layers.18.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
916
  "vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
917
  "vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
918
  "vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
923
  "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
924
  "vision_model.encoder.layers.19.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
925
  "vision_model.encoder.layers.19.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
926
+ "vision_model.encoder.layers.19.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
927
  "vision_model.encoder.layers.19.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
928
  "vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
929
  "vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
930
  "vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
935
  "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
936
  "vision_model.encoder.layers.2.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
937
  "vision_model.encoder.layers.2.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
938
+ "vision_model.encoder.layers.2.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
939
  "vision_model.encoder.layers.2.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
940
  "vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
941
  "vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
942
  "vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
947
  "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
948
  "vision_model.encoder.layers.20.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
949
  "vision_model.encoder.layers.20.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
950
+ "vision_model.encoder.layers.20.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
951
  "vision_model.encoder.layers.20.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
952
  "vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
953
  "vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
954
  "vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
959
  "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
960
  "vision_model.encoder.layers.21.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
961
  "vision_model.encoder.layers.21.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
962
+ "vision_model.encoder.layers.21.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
963
  "vision_model.encoder.layers.21.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
964
  "vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
965
  "vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
966
  "vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
971
  "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
972
  "vision_model.encoder.layers.22.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
973
  "vision_model.encoder.layers.22.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
974
+ "vision_model.encoder.layers.22.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
975
  "vision_model.encoder.layers.22.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
976
  "vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
977
  "vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
978
  "vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
983
  "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
984
  "vision_model.encoder.layers.23.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
985
  "vision_model.encoder.layers.23.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
986
+ "vision_model.encoder.layers.23.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
987
  "vision_model.encoder.layers.23.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
988
  "vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
989
  "vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
990
  "vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
995
  "vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
996
  "vision_model.encoder.layers.24.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
997
  "vision_model.encoder.layers.24.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
998
+ "vision_model.encoder.layers.24.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
999
  "vision_model.encoder.layers.24.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1000
  "vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1001
  "vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1002
  "vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1007
  "vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1008
  "vision_model.encoder.layers.25.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1009
  "vision_model.encoder.layers.25.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1010
+ "vision_model.encoder.layers.25.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1011
  "vision_model.encoder.layers.25.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1012
  "vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1013
  "vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1014
  "vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1019
  "vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1020
  "vision_model.encoder.layers.26.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1021
  "vision_model.encoder.layers.26.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1022
+ "vision_model.encoder.layers.26.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1023
  "vision_model.encoder.layers.26.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1024
  "vision_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1025
  "vision_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1026
  "vision_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1031
  "vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1032
  "vision_model.encoder.layers.27.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1033
  "vision_model.encoder.layers.27.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1034
+ "vision_model.encoder.layers.27.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1035
  "vision_model.encoder.layers.27.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1036
  "vision_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1037
  "vision_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1038
  "vision_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1043
  "vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1044
  "vision_model.encoder.layers.28.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1045
  "vision_model.encoder.layers.28.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1046
+ "vision_model.encoder.layers.28.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1047
  "vision_model.encoder.layers.28.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1048
  "vision_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1049
  "vision_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1050
  "vision_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1055
  "vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1056
  "vision_model.encoder.layers.29.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1057
  "vision_model.encoder.layers.29.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1058
+ "vision_model.encoder.layers.29.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1059
  "vision_model.encoder.layers.29.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1060
  "vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1061
  "vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1062
  "vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1067
  "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1068
  "vision_model.encoder.layers.3.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1069
  "vision_model.encoder.layers.3.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1070
+ "vision_model.encoder.layers.3.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1071
  "vision_model.encoder.layers.3.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1072
  "vision_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1073
  "vision_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1074
  "vision_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1079
  "vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1080
  "vision_model.encoder.layers.30.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1081
  "vision_model.encoder.layers.30.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1082
+ "vision_model.encoder.layers.30.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1083
  "vision_model.encoder.layers.30.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1084
  "vision_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1085
  "vision_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1086
  "vision_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1091
  "vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1092
  "vision_model.encoder.layers.31.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1093
  "vision_model.encoder.layers.31.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1094
+ "vision_model.encoder.layers.31.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1095
  "vision_model.encoder.layers.31.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1096
  "vision_model.encoder.layers.32.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1097
  "vision_model.encoder.layers.32.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1098
  "vision_model.encoder.layers.32.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1103
  "vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1104
  "vision_model.encoder.layers.32.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1105
  "vision_model.encoder.layers.32.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1106
+ "vision_model.encoder.layers.32.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1107
  "vision_model.encoder.layers.32.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1108
  "vision_model.encoder.layers.33.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1109
  "vision_model.encoder.layers.33.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1110
  "vision_model.encoder.layers.33.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1115
  "vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1116
  "vision_model.encoder.layers.33.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1117
  "vision_model.encoder.layers.33.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1118
+ "vision_model.encoder.layers.33.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1119
  "vision_model.encoder.layers.33.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1120
  "vision_model.encoder.layers.34.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1121
  "vision_model.encoder.layers.34.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1122
  "vision_model.encoder.layers.34.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1127
  "vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1128
  "vision_model.encoder.layers.34.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1129
  "vision_model.encoder.layers.34.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1130
+ "vision_model.encoder.layers.34.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1131
  "vision_model.encoder.layers.34.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1132
  "vision_model.encoder.layers.35.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1133
  "vision_model.encoder.layers.35.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1134
  "vision_model.encoder.layers.35.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1139
  "vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1140
  "vision_model.encoder.layers.35.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1141
  "vision_model.encoder.layers.35.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1142
+ "vision_model.encoder.layers.35.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1143
  "vision_model.encoder.layers.35.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1144
  "vision_model.encoder.layers.36.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1145
  "vision_model.encoder.layers.36.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1146
  "vision_model.encoder.layers.36.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1151
  "vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1152
  "vision_model.encoder.layers.36.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1153
  "vision_model.encoder.layers.36.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1154
+ "vision_model.encoder.layers.36.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1155
  "vision_model.encoder.layers.36.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1156
  "vision_model.encoder.layers.37.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1157
  "vision_model.encoder.layers.37.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1158
  "vision_model.encoder.layers.37.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1163
  "vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1164
  "vision_model.encoder.layers.37.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1165
  "vision_model.encoder.layers.37.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1166
+ "vision_model.encoder.layers.37.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1167
  "vision_model.encoder.layers.37.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1168
  "vision_model.encoder.layers.38.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1169
  "vision_model.encoder.layers.38.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1170
  "vision_model.encoder.layers.38.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1175
  "vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1176
  "vision_model.encoder.layers.38.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1177
  "vision_model.encoder.layers.38.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1178
+ "vision_model.encoder.layers.38.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1179
  "vision_model.encoder.layers.38.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1180
  "vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1181
  "vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1182
  "vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1187
  "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1188
  "vision_model.encoder.layers.4.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1189
  "vision_model.encoder.layers.4.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1190
+ "vision_model.encoder.layers.4.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1191
  "vision_model.encoder.layers.4.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1192
  "vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1193
  "vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1194
  "vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1199
  "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1200
  "vision_model.encoder.layers.5.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1201
  "vision_model.encoder.layers.5.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1202
+ "vision_model.encoder.layers.5.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1203
  "vision_model.encoder.layers.5.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1204
  "vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1205
  "vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1206
  "vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1211
  "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1212
  "vision_model.encoder.layers.6.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1213
  "vision_model.encoder.layers.6.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1214
+ "vision_model.encoder.layers.6.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1215
  "vision_model.encoder.layers.6.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1216
  "vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1217
  "vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1218
  "vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1223
  "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1224
  "vision_model.encoder.layers.7.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1225
  "vision_model.encoder.layers.7.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1226
+ "vision_model.encoder.layers.7.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1227
  "vision_model.encoder.layers.7.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1228
  "vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1229
  "vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1230
  "vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1235
  "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1236
  "vision_model.encoder.layers.8.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1237
  "vision_model.encoder.layers.8.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1238
+ "vision_model.encoder.layers.8.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1239
  "vision_model.encoder.layers.8.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1240
  "vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00004.bin",
1241
  "vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00004.bin",
1242
  "vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00004.bin",
 
1247
  "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1248
  "vision_model.encoder.layers.9.self_attn.projection.bias": "pytorch_model-00001-of-00004.bin",
1249
  "vision_model.encoder.layers.9.self_attn.projection.weight": "pytorch_model-00001-of-00004.bin",
1250
+ "vision_model.encoder.layers.9.self_attn.qkv.bias": "pytorch_model-00001-of-00004.bin",
1251
  "vision_model.encoder.layers.9.self_attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
 
1252
  "vision_model.post_layernorm.bias": "pytorch_model-00001-of-00004.bin",
1253
  "vision_model.post_layernorm.weight": "pytorch_model-00001-of-00004.bin"
1254
  }