Hugging Face's logo

n0kovo
/
llama-joycaption-beta-one-hf-llava-mlx-8Bit

Image-Text-to-Text
MLX
Safetensors
llava
captioning
conversational
Model card Files
xet
 Community
1
n0kovo commited on
Commit
252d71c
·
verified ·
1 Parent(s): fb1ce0d

Update model.safetensors.index.json

Browse files
Files changed (1) hide show
  1. model.safetensors.index.json +737 -3
model.safetensors.index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "metadata": {
3
- "total_size": 8532402176,
4
- "total_parameters": 8030261248
5
  },
6
  "weight_map": {
7
  "language_model.lm_head.biases": "model-00002-of-00002.safetensors",
@@ -746,6 +746,740 @@
746
  "language_model.model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
747
  "language_model.model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
748
  "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
749
- "language_model.model.norm.weight": "model-00002-of-00002.safetensors"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
750
  }
751
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 9145155336,
4
+ "total_parameters": 8260182884
5
  },
6
  "weight_map": {
7
  "language_model.lm_head.biases": "model-00002-of-00002.safetensors",
 
746
  "language_model.model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
747
  "language_model.model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
748
  "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
749
+ "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
750
+
751
+
752
+ "multi_modal_projector.linear_1.bias": "vision_model.safetensors",
753
+ "multi_modal_projector.linear_1.biases": "vision_model.safetensors",
754
+ "multi_modal_projector.linear_1.scales": "vision_model.safetensors",
755
+ "multi_modal_projector.linear_1.weight": "vision_model.safetensors",
756
+ "multi_modal_projector.linear_2.bias": "vision_model.safetensors",
757
+ "multi_modal_projector.linear_2.biases": "vision_model.safetensors",
758
+ "multi_modal_projector.linear_2.scales": "vision_model.safetensors",
759
+ "multi_modal_projector.linear_2.weight": "vision_model.safetensors",
760
+ "vision_tower.vision_model.embeddings.patch_embedding.bias": "vision_model.safetensors",
761
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "vision_model.safetensors",
762
+ "vision_tower.vision_model.embeddings.position_embedding.biases": "vision_model.safetensors",
763
+ "vision_tower.vision_model.embeddings.position_embedding.scales": "vision_model.safetensors",
764
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "vision_model.safetensors",
765
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "vision_model.safetensors",
766
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "vision_model.safetensors",
767
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "vision_model.safetensors",
768
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "vision_model.safetensors",
769
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "vision_model.safetensors",
770
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.biases": "vision_model.safetensors",
771
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.scales": "vision_model.safetensors",
772
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "vision_model.safetensors",
773
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "vision_model.safetensors",
774
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "vision_model.safetensors",
775
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "vision_model.safetensors",
776
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.biases": "vision_model.safetensors",
777
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.scales": "vision_model.safetensors",
778
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "vision_model.safetensors",
779
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "vision_model.safetensors",
780
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.biases": "vision_model.safetensors",
781
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.scales": "vision_model.safetensors",
782
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "vision_model.safetensors",
783
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "vision_model.safetensors",
784
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.biases": "vision_model.safetensors",
785
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.scales": "vision_model.safetensors",
786
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "vision_model.safetensors",
787
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "vision_model.safetensors",
788
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.biases": "vision_model.safetensors",
789
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.scales": "vision_model.safetensors",
790
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "vision_model.safetensors",
791
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "vision_model.safetensors",
792
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "vision_model.safetensors",
793
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "vision_model.safetensors",
794
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "vision_model.safetensors",
795
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "vision_model.safetensors",
796
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.biases": "vision_model.safetensors",
797
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.scales": "vision_model.safetensors",
798
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "vision_model.safetensors",
799
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "vision_model.safetensors",
800
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "vision_model.safetensors",
801
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "vision_model.safetensors",
802
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.biases": "vision_model.safetensors",
803
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.scales": "vision_model.safetensors",
804
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "vision_model.safetensors",
805
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "vision_model.safetensors",
806
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.biases": "vision_model.safetensors",
807
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.scales": "vision_model.safetensors",
808
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "vision_model.safetensors",
809
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "vision_model.safetensors",
810
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.biases": "vision_model.safetensors",
811
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.scales": "vision_model.safetensors",
812
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "vision_model.safetensors",
813
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "vision_model.safetensors",
814
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.biases": "vision_model.safetensors",
815
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.scales": "vision_model.safetensors",
816
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "vision_model.safetensors",
817
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "vision_model.safetensors",
818
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "vision_model.safetensors",
819
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "vision_model.safetensors",
820
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "vision_model.safetensors",
821
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "vision_model.safetensors",
822
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.biases": "vision_model.safetensors",
823
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.scales": "vision_model.safetensors",
824
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "vision_model.safetensors",
825
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "vision_model.safetensors",
826
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "vision_model.safetensors",
827
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "vision_model.safetensors",
828
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.biases": "vision_model.safetensors",
829
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.scales": "vision_model.safetensors",
830
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "vision_model.safetensors",
831
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "vision_model.safetensors",
832
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.biases": "vision_model.safetensors",
833
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.scales": "vision_model.safetensors",
834
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "vision_model.safetensors",
835
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "vision_model.safetensors",
836
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.biases": "vision_model.safetensors",
837
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.scales": "vision_model.safetensors",
838
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "vision_model.safetensors",
839
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "vision_model.safetensors",
840
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.biases": "vision_model.safetensors",
841
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.scales": "vision_model.safetensors",
842
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "vision_model.safetensors",
843
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "vision_model.safetensors",
844
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "vision_model.safetensors",
845
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "vision_model.safetensors",
846
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "vision_model.safetensors",
847
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "vision_model.safetensors",
848
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.biases": "vision_model.safetensors",
849
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.scales": "vision_model.safetensors",
850
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "vision_model.safetensors",
851
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "vision_model.safetensors",
852
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "vision_model.safetensors",
853
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "vision_model.safetensors",
854
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.biases": "vision_model.safetensors",
855
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.scales": "vision_model.safetensors",
856
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "vision_model.safetensors",
857
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "vision_model.safetensors",
858
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.biases": "vision_model.safetensors",
859
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.scales": "vision_model.safetensors",
860
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "vision_model.safetensors",
861
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "vision_model.safetensors",
862
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.biases": "vision_model.safetensors",
863
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.scales": "vision_model.safetensors",
864
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "vision_model.safetensors",
865
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "vision_model.safetensors",
866
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.biases": "vision_model.safetensors",
867
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.scales": "vision_model.safetensors",
868
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "vision_model.safetensors",
869
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "vision_model.safetensors",
870
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "vision_model.safetensors",
871
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "vision_model.safetensors",
872
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "vision_model.safetensors",
873
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "vision_model.safetensors",
874
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.biases": "vision_model.safetensors",
875
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.scales": "vision_model.safetensors",
876
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "vision_model.safetensors",
877
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "vision_model.safetensors",
878
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "vision_model.safetensors",
879
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "vision_model.safetensors",
880
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.biases": "vision_model.safetensors",
881
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.scales": "vision_model.safetensors",
882
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "vision_model.safetensors",
883
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "vision_model.safetensors",
884
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.biases": "vision_model.safetensors",
885
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.scales": "vision_model.safetensors",
886
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "vision_model.safetensors",
887
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "vision_model.safetensors",
888
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.biases": "vision_model.safetensors",
889
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.scales": "vision_model.safetensors",
890
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "vision_model.safetensors",
891
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "vision_model.safetensors",
892
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.biases": "vision_model.safetensors",
893
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.scales": "vision_model.safetensors",
894
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "vision_model.safetensors",
895
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "vision_model.safetensors",
896
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "vision_model.safetensors",
897
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "vision_model.safetensors",
898
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "vision_model.safetensors",
899
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "vision_model.safetensors",
900
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.biases": "vision_model.safetensors",
901
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.scales": "vision_model.safetensors",
902
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "vision_model.safetensors",
903
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "vision_model.safetensors",
904
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "vision_model.safetensors",
905
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "vision_model.safetensors",
906
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.biases": "vision_model.safetensors",
907
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.scales": "vision_model.safetensors",
908
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "vision_model.safetensors",
909
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "vision_model.safetensors",
910
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.biases": "vision_model.safetensors",
911
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.scales": "vision_model.safetensors",
912
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "vision_model.safetensors",
913
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "vision_model.safetensors",
914
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.biases": "vision_model.safetensors",
915
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.scales": "vision_model.safetensors",
916
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "vision_model.safetensors",
917
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "vision_model.safetensors",
918
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.biases": "vision_model.safetensors",
919
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.scales": "vision_model.safetensors",
920
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "vision_model.safetensors",
921
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "vision_model.safetensors",
922
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "vision_model.safetensors",
923
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "vision_model.safetensors",
924
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "vision_model.safetensors",
925
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "vision_model.safetensors",
926
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.biases": "vision_model.safetensors",
927
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.scales": "vision_model.safetensors",
928
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "vision_model.safetensors",
929
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "vision_model.safetensors",
930
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "vision_model.safetensors",
931
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "vision_model.safetensors",
932
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.biases": "vision_model.safetensors",
933
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.scales": "vision_model.safetensors",
934
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "vision_model.safetensors",
935
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "vision_model.safetensors",
936
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.biases": "vision_model.safetensors",
937
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.scales": "vision_model.safetensors",
938
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "vision_model.safetensors",
939
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "vision_model.safetensors",
940
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.biases": "vision_model.safetensors",
941
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.scales": "vision_model.safetensors",
942
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "vision_model.safetensors",
943
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "vision_model.safetensors",
944
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.biases": "vision_model.safetensors",
945
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.scales": "vision_model.safetensors",
946
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "vision_model.safetensors",
947
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "vision_model.safetensors",
948
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "vision_model.safetensors",
949
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "vision_model.safetensors",
950
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "vision_model.safetensors",
951
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "vision_model.safetensors",
952
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.biases": "vision_model.safetensors",
953
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.scales": "vision_model.safetensors",
954
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "vision_model.safetensors",
955
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "vision_model.safetensors",
956
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "vision_model.safetensors",
957
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "vision_model.safetensors",
958
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.biases": "vision_model.safetensors",
959
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.scales": "vision_model.safetensors",
960
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "vision_model.safetensors",
961
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "vision_model.safetensors",
962
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.biases": "vision_model.safetensors",
963
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.scales": "vision_model.safetensors",
964
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "vision_model.safetensors",
965
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "vision_model.safetensors",
966
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.biases": "vision_model.safetensors",
967
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.scales": "vision_model.safetensors",
968
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "vision_model.safetensors",
969
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "vision_model.safetensors",
970
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.biases": "vision_model.safetensors",
971
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.scales": "vision_model.safetensors",
972
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "vision_model.safetensors",
973
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "vision_model.safetensors",
974
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "vision_model.safetensors",
975
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "vision_model.safetensors",
976
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "vision_model.safetensors",
977
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "vision_model.safetensors",
978
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.biases": "vision_model.safetensors",
979
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.scales": "vision_model.safetensors",
980
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "vision_model.safetensors",
981
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "vision_model.safetensors",
982
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "vision_model.safetensors",
983
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "vision_model.safetensors",
984
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.biases": "vision_model.safetensors",
985
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.scales": "vision_model.safetensors",
986
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "vision_model.safetensors",
987
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "vision_model.safetensors",
988
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.biases": "vision_model.safetensors",
989
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.scales": "vision_model.safetensors",
990
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "vision_model.safetensors",
991
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "vision_model.safetensors",
992
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.biases": "vision_model.safetensors",
993
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.scales": "vision_model.safetensors",
994
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "vision_model.safetensors",
995
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "vision_model.safetensors",
996
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.biases": "vision_model.safetensors",
997
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.scales": "vision_model.safetensors",
998
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "vision_model.safetensors",
999
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "vision_model.safetensors",
1000
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "vision_model.safetensors",
1001
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "vision_model.safetensors",
1002
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "vision_model.safetensors",
1003
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "vision_model.safetensors",
1004
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.biases": "vision_model.safetensors",
1005
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.scales": "vision_model.safetensors",
1006
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "vision_model.safetensors",
1007
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "vision_model.safetensors",
1008
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "vision_model.safetensors",
1009
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "vision_model.safetensors",
1010
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.biases": "vision_model.safetensors",
1011
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.scales": "vision_model.safetensors",
1012
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "vision_model.safetensors",
1013
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "vision_model.safetensors",
1014
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.biases": "vision_model.safetensors",
1015
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.scales": "vision_model.safetensors",
1016
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "vision_model.safetensors",
1017
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "vision_model.safetensors",
1018
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.biases": "vision_model.safetensors",
1019
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.scales": "vision_model.safetensors",
1020
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "vision_model.safetensors",
1021
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "vision_model.safetensors",
1022
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.biases": "vision_model.safetensors",
1023
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.scales": "vision_model.safetensors",
1024
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "vision_model.safetensors",
1025
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "vision_model.safetensors",
1026
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "vision_model.safetensors",
1027
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "vision_model.safetensors",
1028
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "vision_model.safetensors",
1029
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "vision_model.safetensors",
1030
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.biases": "vision_model.safetensors",
1031
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.scales": "vision_model.safetensors",
1032
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "vision_model.safetensors",
1033
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "vision_model.safetensors",
1034
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "vision_model.safetensors",
1035
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "vision_model.safetensors",
1036
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.biases": "vision_model.safetensors",
1037
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.scales": "vision_model.safetensors",
1038
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "vision_model.safetensors",
1039
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "vision_model.safetensors",
1040
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.biases": "vision_model.safetensors",
1041
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.scales": "vision_model.safetensors",
1042
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "vision_model.safetensors",
1043
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "vision_model.safetensors",
1044
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.biases": "vision_model.safetensors",
1045
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.scales": "vision_model.safetensors",
1046
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "vision_model.safetensors",
1047
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "vision_model.safetensors",
1048
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.biases": "vision_model.safetensors",
1049
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.scales": "vision_model.safetensors",
1050
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "vision_model.safetensors",
1051
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "vision_model.safetensors",
1052
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "vision_model.safetensors",
1053
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "vision_model.safetensors",
1054
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "vision_model.safetensors",
1055
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "vision_model.safetensors",
1056
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.biases": "vision_model.safetensors",
1057
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.scales": "vision_model.safetensors",
1058
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "vision_model.safetensors",
1059
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "vision_model.safetensors",
1060
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "vision_model.safetensors",
1061
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "vision_model.safetensors",
1062
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.biases": "vision_model.safetensors",
1063
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.scales": "vision_model.safetensors",
1064
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "vision_model.safetensors",
1065
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "vision_model.safetensors",
1066
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.biases": "vision_model.safetensors",
1067
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.scales": "vision_model.safetensors",
1068
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "vision_model.safetensors",
1069
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "vision_model.safetensors",
1070
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.biases": "vision_model.safetensors",
1071
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.scales": "vision_model.safetensors",
1072
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "vision_model.safetensors",
1073
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "vision_model.safetensors",
1074
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.biases": "vision_model.safetensors",
1075
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.scales": "vision_model.safetensors",
1076
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "vision_model.safetensors",
1077
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "vision_model.safetensors",
1078
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "vision_model.safetensors",
1079
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "vision_model.safetensors",
1080
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "vision_model.safetensors",
1081
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "vision_model.safetensors",
1082
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.biases": "vision_model.safetensors",
1083
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.scales": "vision_model.safetensors",
1084
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "vision_model.safetensors",
1085
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "vision_model.safetensors",
1086
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "vision_model.safetensors",
1087
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "vision_model.safetensors",
1088
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.biases": "vision_model.safetensors",
1089
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.scales": "vision_model.safetensors",
1090
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "vision_model.safetensors",
1091
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "vision_model.safetensors",
1092
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.biases": "vision_model.safetensors",
1093
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.scales": "vision_model.safetensors",
1094
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "vision_model.safetensors",
1095
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "vision_model.safetensors",
1096
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.biases": "vision_model.safetensors",
1097
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.scales": "vision_model.safetensors",
1098
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "vision_model.safetensors",
1099
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "vision_model.safetensors",
1100
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.biases": "vision_model.safetensors",
1101
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.scales": "vision_model.safetensors",
1102
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "vision_model.safetensors",
1103
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "vision_model.safetensors",
1104
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "vision_model.safetensors",
1105
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "vision_model.safetensors",
1106
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "vision_model.safetensors",
1107
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "vision_model.safetensors",
1108
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.biases": "vision_model.safetensors",
1109
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.scales": "vision_model.safetensors",
1110
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "vision_model.safetensors",
1111
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "vision_model.safetensors",
1112
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "vision_model.safetensors",
1113
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "vision_model.safetensors",
1114
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.biases": "vision_model.safetensors",
1115
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.scales": "vision_model.safetensors",
1116
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "vision_model.safetensors",
1117
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "vision_model.safetensors",
1118
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.biases": "vision_model.safetensors",
1119
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.scales": "vision_model.safetensors",
1120
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "vision_model.safetensors",
1121
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "vision_model.safetensors",
1122
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.biases": "vision_model.safetensors",
1123
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.scales": "vision_model.safetensors",
1124
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "vision_model.safetensors",
1125
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "vision_model.safetensors",
1126
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.biases": "vision_model.safetensors",
1127
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.scales": "vision_model.safetensors",
1128
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "vision_model.safetensors",
1129
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "vision_model.safetensors",
1130
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "vision_model.safetensors",
1131
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "vision_model.safetensors",
1132
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "vision_model.safetensors",
1133
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "vision_model.safetensors",
1134
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.biases": "vision_model.safetensors",
1135
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.scales": "vision_model.safetensors",
1136
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "vision_model.safetensors",
1137
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "vision_model.safetensors",
1138
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "vision_model.safetensors",
1139
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "vision_model.safetensors",
1140
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.biases": "vision_model.safetensors",
1141
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.scales": "vision_model.safetensors",
1142
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "vision_model.safetensors",
1143
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "vision_model.safetensors",
1144
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.biases": "vision_model.safetensors",
1145
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.scales": "vision_model.safetensors",
1146
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "vision_model.safetensors",
1147
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "vision_model.safetensors",
1148
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.biases": "vision_model.safetensors",
1149
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.scales": "vision_model.safetensors",
1150
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "vision_model.safetensors",
1151
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "vision_model.safetensors",
1152
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.biases": "vision_model.safetensors",
1153
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.scales": "vision_model.safetensors",
1154
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "vision_model.safetensors",
1155
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "vision_model.safetensors",
1156
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "vision_model.safetensors",
1157
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "vision_model.safetensors",
1158
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "vision_model.safetensors",
1159
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "vision_model.safetensors",
1160
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.biases": "vision_model.safetensors",
1161
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.scales": "vision_model.safetensors",
1162
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "vision_model.safetensors",
1163
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "vision_model.safetensors",
1164
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "vision_model.safetensors",
1165
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "vision_model.safetensors",
1166
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.biases": "vision_model.safetensors",
1167
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.scales": "vision_model.safetensors",
1168
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "vision_model.safetensors",
1169
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "vision_model.safetensors",
1170
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.biases": "vision_model.safetensors",
1171
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.scales": "vision_model.safetensors",
1172
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "vision_model.safetensors",
1173
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "vision_model.safetensors",
1174
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.biases": "vision_model.safetensors",
1175
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.scales": "vision_model.safetensors",
1176
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "vision_model.safetensors",
1177
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "vision_model.safetensors",
1178
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.biases": "vision_model.safetensors",
1179
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.scales": "vision_model.safetensors",
1180
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "vision_model.safetensors",
1181
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "vision_model.safetensors",
1182
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "vision_model.safetensors",
1183
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "vision_model.safetensors",
1184
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "vision_model.safetensors",
1185
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "vision_model.safetensors",
1186
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.biases": "vision_model.safetensors",
1187
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.scales": "vision_model.safetensors",
1188
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "vision_model.safetensors",
1189
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "vision_model.safetensors",
1190
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "vision_model.safetensors",
1191
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "vision_model.safetensors",
1192
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.biases": "vision_model.safetensors",
1193
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.scales": "vision_model.safetensors",
1194
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "vision_model.safetensors",
1195
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "vision_model.safetensors",
1196
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.biases": "vision_model.safetensors",
1197
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.scales": "vision_model.safetensors",
1198
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "vision_model.safetensors",
1199
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "vision_model.safetensors",
1200
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.biases": "vision_model.safetensors",
1201
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.scales": "vision_model.safetensors",
1202
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "vision_model.safetensors",
1203
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "vision_model.safetensors",
1204
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.biases": "vision_model.safetensors",
1205
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.scales": "vision_model.safetensors",
1206
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "vision_model.safetensors",
1207
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "vision_model.safetensors",
1208
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "vision_model.safetensors",
1209
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "vision_model.safetensors",
1210
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "vision_model.safetensors",
1211
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "vision_model.safetensors",
1212
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.biases": "vision_model.safetensors",
1213
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.scales": "vision_model.safetensors",
1214
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "vision_model.safetensors",
1215
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "vision_model.safetensors",
1216
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "vision_model.safetensors",
1217
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "vision_model.safetensors",
1218
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.biases": "vision_model.safetensors",
1219
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.scales": "vision_model.safetensors",
1220
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "vision_model.safetensors",
1221
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "vision_model.safetensors",
1222
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.biases": "vision_model.safetensors",
1223
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.scales": "vision_model.safetensors",
1224
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "vision_model.safetensors",
1225
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "vision_model.safetensors",
1226
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.biases": "vision_model.safetensors",
1227
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.scales": "vision_model.safetensors",
1228
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "vision_model.safetensors",
1229
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "vision_model.safetensors",
1230
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.biases": "vision_model.safetensors",
1231
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.scales": "vision_model.safetensors",
1232
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "vision_model.safetensors",
1233
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "vision_model.safetensors",
1234
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "vision_model.safetensors",
1235
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "vision_model.safetensors",
1236
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "vision_model.safetensors",
1237
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "vision_model.safetensors",
1238
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.biases": "vision_model.safetensors",
1239
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.scales": "vision_model.safetensors",
1240
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "vision_model.safetensors",
1241
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "vision_model.safetensors",
1242
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "vision_model.safetensors",
1243
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "vision_model.safetensors",
1244
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.biases": "vision_model.safetensors",
1245
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.scales": "vision_model.safetensors",
1246
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "vision_model.safetensors",
1247
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "vision_model.safetensors",
1248
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.biases": "vision_model.safetensors",
1249
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.scales": "vision_model.safetensors",
1250
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "vision_model.safetensors",
1251
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "vision_model.safetensors",
1252
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.biases": "vision_model.safetensors",
1253
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.scales": "vision_model.safetensors",
1254
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "vision_model.safetensors",
1255
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "vision_model.safetensors",
1256
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.biases": "vision_model.safetensors",
1257
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.scales": "vision_model.safetensors",
1258
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "vision_model.safetensors",
1259
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "vision_model.safetensors",
1260
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "vision_model.safetensors",
1261
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "vision_model.safetensors",
1262
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "vision_model.safetensors",
1263
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "vision_model.safetensors",
1264
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.biases": "vision_model.safetensors",
1265
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.scales": "vision_model.safetensors",
1266
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "vision_model.safetensors",
1267
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "vision_model.safetensors",
1268
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "vision_model.safetensors",
1269
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "vision_model.safetensors",
1270
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.biases": "vision_model.safetensors",
1271
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.scales": "vision_model.safetensors",
1272
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "vision_model.safetensors",
1273
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "vision_model.safetensors",
1274
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.biases": "vision_model.safetensors",
1275
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.scales": "vision_model.safetensors",
1276
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "vision_model.safetensors",
1277
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "vision_model.safetensors",
1278
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.biases": "vision_model.safetensors",
1279
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.scales": "vision_model.safetensors",
1280
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "vision_model.safetensors",
1281
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "vision_model.safetensors",
1282
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.biases": "vision_model.safetensors",
1283
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.scales": "vision_model.safetensors",
1284
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "vision_model.safetensors",
1285
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "vision_model.safetensors",
1286
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "vision_model.safetensors",
1287
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "vision_model.safetensors",
1288
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "vision_model.safetensors",
1289
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "vision_model.safetensors",
1290
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.biases": "vision_model.safetensors",
1291
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.scales": "vision_model.safetensors",
1292
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "vision_model.safetensors",
1293
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "vision_model.safetensors",
1294
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "vision_model.safetensors",
1295
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "vision_model.safetensors",
1296
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.biases": "vision_model.safetensors",
1297
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.scales": "vision_model.safetensors",
1298
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "vision_model.safetensors",
1299
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "vision_model.safetensors",
1300
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.biases": "vision_model.safetensors",
1301
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.scales": "vision_model.safetensors",
1302
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "vision_model.safetensors",
1303
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "vision_model.safetensors",
1304
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.biases": "vision_model.safetensors",
1305
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.scales": "vision_model.safetensors",
1306
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "vision_model.safetensors",
1307
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "vision_model.safetensors",
1308
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.biases": "vision_model.safetensors",
1309
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.scales": "vision_model.safetensors",
1310
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "vision_model.safetensors",
1311
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "vision_model.safetensors",
1312
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "vision_model.safetensors",
1313
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "vision_model.safetensors",
1314
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "vision_model.safetensors",
1315
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "vision_model.safetensors",
1316
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.biases": "vision_model.safetensors",
1317
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.scales": "vision_model.safetensors",
1318
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "vision_model.safetensors",
1319
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "vision_model.safetensors",
1320
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "vision_model.safetensors",
1321
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "vision_model.safetensors",
1322
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.biases": "vision_model.safetensors",
1323
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.scales": "vision_model.safetensors",
1324
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "vision_model.safetensors",
1325
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "vision_model.safetensors",
1326
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.biases": "vision_model.safetensors",
1327
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.scales": "vision_model.safetensors",
1328
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "vision_model.safetensors",
1329
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "vision_model.safetensors",
1330
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.biases": "vision_model.safetensors",
1331
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.scales": "vision_model.safetensors",
1332
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "vision_model.safetensors",
1333
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "vision_model.safetensors",
1334
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.biases": "vision_model.safetensors",
1335
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.scales": "vision_model.safetensors",
1336
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "vision_model.safetensors",
1337
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "vision_model.safetensors",
1338
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "vision_model.safetensors",
1339
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "vision_model.safetensors",
1340
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "vision_model.safetensors",
1341
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "vision_model.safetensors",
1342
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.biases": "vision_model.safetensors",
1343
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.scales": "vision_model.safetensors",
1344
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "vision_model.safetensors",
1345
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "vision_model.safetensors",
1346
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "vision_model.safetensors",
1347
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "vision_model.safetensors",
1348
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.biases": "vision_model.safetensors",
1349
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.scales": "vision_model.safetensors",
1350
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "vision_model.safetensors",
1351
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "vision_model.safetensors",
1352
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.biases": "vision_model.safetensors",
1353
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.scales": "vision_model.safetensors",
1354
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "vision_model.safetensors",
1355
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "vision_model.safetensors",
1356
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.biases": "vision_model.safetensors",
1357
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.scales": "vision_model.safetensors",
1358
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "vision_model.safetensors",
1359
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "vision_model.safetensors",
1360
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.biases": "vision_model.safetensors",
1361
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.scales": "vision_model.safetensors",
1362
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "vision_model.safetensors",
1363
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "vision_model.safetensors",
1364
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "vision_model.safetensors",
1365
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "vision_model.safetensors",
1366
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "vision_model.safetensors",
1367
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "vision_model.safetensors",
1368
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.biases": "vision_model.safetensors",
1369
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.scales": "vision_model.safetensors",
1370
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "vision_model.safetensors",
1371
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "vision_model.safetensors",
1372
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "vision_model.safetensors",
1373
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "vision_model.safetensors",
1374
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.biases": "vision_model.safetensors",
1375
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.scales": "vision_model.safetensors",
1376
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "vision_model.safetensors",
1377
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "vision_model.safetensors",
1378
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.biases": "vision_model.safetensors",
1379
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.scales": "vision_model.safetensors",
1380
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "vision_model.safetensors",
1381
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "vision_model.safetensors",
1382
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.biases": "vision_model.safetensors",
1383
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.scales": "vision_model.safetensors",
1384
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "vision_model.safetensors",
1385
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "vision_model.safetensors",
1386
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.biases": "vision_model.safetensors",
1387
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.scales": "vision_model.safetensors",
1388
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "vision_model.safetensors",
1389
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "vision_model.safetensors",
1390
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "vision_model.safetensors",
1391
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "vision_model.safetensors",
1392
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "vision_model.safetensors",
1393
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "vision_model.safetensors",
1394
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.biases": "vision_model.safetensors",
1395
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.scales": "vision_model.safetensors",
1396
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "vision_model.safetensors",
1397
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "vision_model.safetensors",
1398
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "vision_model.safetensors",
1399
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "vision_model.safetensors",
1400
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.biases": "vision_model.safetensors",
1401
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.scales": "vision_model.safetensors",
1402
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "vision_model.safetensors",
1403
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "vision_model.safetensors",
1404
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.biases": "vision_model.safetensors",
1405
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.scales": "vision_model.safetensors",
1406
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "vision_model.safetensors",
1407
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "vision_model.safetensors",
1408
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.biases": "vision_model.safetensors",
1409
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.scales": "vision_model.safetensors",
1410
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "vision_model.safetensors",
1411
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "vision_model.safetensors",
1412
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.biases": "vision_model.safetensors",
1413
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.scales": "vision_model.safetensors",
1414
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "vision_model.safetensors",
1415
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "vision_model.safetensors",
1416
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "vision_model.safetensors",
1417
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "vision_model.safetensors",
1418
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "vision_model.safetensors",
1419
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "vision_model.safetensors",
1420
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.biases": "vision_model.safetensors",
1421
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.scales": "vision_model.safetensors",
1422
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "vision_model.safetensors",
1423
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "vision_model.safetensors",
1424
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "vision_model.safetensors",
1425
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "vision_model.safetensors",
1426
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.biases": "vision_model.safetensors",
1427
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.scales": "vision_model.safetensors",
1428
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "vision_model.safetensors",
1429
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "vision_model.safetensors",
1430
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.biases": "vision_model.safetensors",
1431
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.scales": "vision_model.safetensors",
1432
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "vision_model.safetensors",
1433
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "vision_model.safetensors",
1434
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.biases": "vision_model.safetensors",
1435
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.scales": "vision_model.safetensors",
1436
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "vision_model.safetensors",
1437
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "vision_model.safetensors",
1438
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.biases": "vision_model.safetensors",
1439
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.scales": "vision_model.safetensors",
1440
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "vision_model.safetensors",
1441
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "vision_model.safetensors",
1442
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "vision_model.safetensors",
1443
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "vision_model.safetensors",
1444
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "vision_model.safetensors",
1445
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "vision_model.safetensors",
1446
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.biases": "vision_model.safetensors",
1447
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.scales": "vision_model.safetensors",
1448
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "vision_model.safetensors",
1449
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "vision_model.safetensors",
1450
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "vision_model.safetensors",
1451
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "vision_model.safetensors",
1452
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.biases": "vision_model.safetensors",
1453
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.scales": "vision_model.safetensors",
1454
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "vision_model.safetensors",
1455
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "vision_model.safetensors",
1456
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.biases": "vision_model.safetensors",
1457
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.scales": "vision_model.safetensors",
1458
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "vision_model.safetensors",
1459
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "vision_model.safetensors",
1460
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.biases": "vision_model.safetensors",
1461
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.scales": "vision_model.safetensors",
1462
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "vision_model.safetensors",
1463
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "vision_model.safetensors",
1464
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.biases": "vision_model.safetensors",
1465
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.scales": "vision_model.safetensors",
1466
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "vision_model.safetensors",
1467
+ "vision_tower.vision_model.head.attention.in_proj_bias": "vision_model.safetensors",
1468
+ "vision_tower.vision_model.head.attention.in_proj_weight": "vision_model.safetensors",
1469
+ "vision_tower.vision_model.head.attention.out_proj.bias": "vision_model.safetensors",
1470
+ "vision_tower.vision_model.head.attention.out_proj.biases": "vision_model.safetensors",
1471
+ "vision_tower.vision_model.head.attention.out_proj.scales": "vision_model.safetensors",
1472
+ "vision_tower.vision_model.head.attention.out_proj.weight": "vision_model.safetensors",
1473
+ "vision_tower.vision_model.head.layernorm.bias": "vision_model.safetensors",
1474
+ "vision_tower.vision_model.head.layernorm.weight": "vision_model.safetensors",
1475
+ "vision_tower.vision_model.head.mlp.fc1.bias": "vision_model.safetensors",
1476
+ "vision_tower.vision_model.head.mlp.fc1.biases": "vision_model.safetensors",
1477
+ "vision_tower.vision_model.head.mlp.fc1.scales": "vision_model.safetensors",
1478
+ "vision_tower.vision_model.head.mlp.fc1.weight": "vision_model.safetensors",
1479
+ "vision_tower.vision_model.head.mlp.fc2.bias": "vision_model.safetensors",
1480
+ "vision_tower.vision_model.head.mlp.fc2.weight": "vision_model.safetensors",
1481
+ "vision_tower.vision_model.head.probe": "vision_model.safetensors",
1482
+ "vision_tower.vision_model.post_layernorm.bias": "vision_model.safetensors",
1483
+ "vision_tower.vision_model.post_layernorm.weight": "vision_model.safetensors"
1484
  }
1485
  }