Hugging Face's logo

charlesdj
/
CSR_LLaVA_1.5_13b_1Iteration

Model card Files
xet
 Community
Yiyang Zhou commited on
Commit
8c9c964
·
1 Parent(s): ace178f

update

Browse files
Files changed (14) hide show
  1. README.md +3 -0
  2. key_mapping_13b.json +760 -0
  3. llava_merged_dpo_13b_1epoch_1iteration/config.json +49 -0
  4. llava_merged_dpo_13b_1epoch_1iteration/generation_config.json +8 -0
  5. llava_merged_dpo_13b_1epoch_1iteration/pytorch_model-00001-of-00003.bin +3 -0
  6. llava_merged_dpo_13b_1epoch_1iteration/pytorch_model-00002-of-00003.bin +3 -0
  7. llava_merged_dpo_13b_1epoch_1iteration/pytorch_model-00003-of-00003.bin +3 -0
  8. llava_merged_dpo_13b_1epoch_1iteration/pytorch_model.bin.index.json +765 -0
  9. llava_merged_dpo_13b_1epoch_1iteration/special_tokens_map.json +24 -0
  10. llava_merged_dpo_13b_1epoch_1iteration/tokenizer.model +3 -0
  11. llava_merged_dpo_13b_1epoch_1iteration/tokenizer_config.json +37 -0
  12. my_dataset12k.json +0 -0
  13. sample.sh +14 -0
  14. sample_tree.py +340 -0
README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
key_mapping_13b.json ADDED
@@ -0,0 +1,760 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "lm_head.weight": "language_model.lm_head.weight",
3
+ "model.embed_tokens.weight": "language_model.model.embed_tokens.weight",
4
+ "model.layers.0.input_layernorm.weight": "language_model.model.layers.0.input_layernorm.weight",
5
+ "model.layers.0.mlp.down_proj.weight": "language_model.model.layers.0.mlp.down_proj.weight",
6
+ "model.layers.0.mlp.gate_proj.weight": "language_model.model.layers.0.mlp.gate_proj.weight",
7
+ "model.layers.0.mlp.up_proj.weight": "language_model.model.layers.0.mlp.up_proj.weight",
8
+ "model.layers.0.post_attention_layernorm.weight": "language_model.model.layers.0.post_attention_layernorm.weight",
9
+ "model.layers.0.self_attn.k_proj.weight": "language_model.model.layers.0.self_attn.k_proj.weight",
10
+ "model.layers.0.self_attn.o_proj.weight": "language_model.model.layers.0.self_attn.o_proj.weight",
11
+ "model.layers.0.self_attn.q_proj.weight": "language_model.model.layers.0.self_attn.q_proj.weight",
12
+ "model.layers.0.self_attn.v_proj.weight": "language_model.model.layers.0.self_attn.v_proj.weight",
13
+ "model.layers.1.input_layernorm.weight": "language_model.model.layers.1.input_layernorm.weight",
14
+ "model.layers.1.mlp.down_proj.weight": "language_model.model.layers.1.mlp.down_proj.weight",
15
+ "model.layers.1.mlp.gate_proj.weight": "language_model.model.layers.1.mlp.gate_proj.weight",
16
+ "model.layers.1.mlp.up_proj.weight": "language_model.model.layers.1.mlp.up_proj.weight",
17
+ "model.layers.1.post_attention_layernorm.weight": "language_model.model.layers.1.post_attention_layernorm.weight",
18
+ "model.layers.1.self_attn.k_proj.weight": "language_model.model.layers.1.self_attn.k_proj.weight",
19
+ "model.layers.1.self_attn.o_proj.weight": "language_model.model.layers.1.self_attn.o_proj.weight",
20
+ "model.layers.1.self_attn.q_proj.weight": "language_model.model.layers.1.self_attn.q_proj.weight",
21
+ "model.layers.1.self_attn.v_proj.weight": "language_model.model.layers.1.self_attn.v_proj.weight",
22
+ "model.layers.10.input_layernorm.weight": "language_model.model.layers.10.input_layernorm.weight",
23
+ "model.layers.10.mlp.down_proj.weight": "language_model.model.layers.10.mlp.down_proj.weight",
24
+ "model.layers.10.mlp.gate_proj.weight": "language_model.model.layers.10.mlp.gate_proj.weight",
25
+ "model.layers.10.mlp.up_proj.weight": "language_model.model.layers.10.mlp.up_proj.weight",
26
+ "model.layers.10.post_attention_layernorm.weight": "language_model.model.layers.10.post_attention_layernorm.weight",
27
+ "model.layers.10.self_attn.k_proj.weight": "language_model.model.layers.10.self_attn.k_proj.weight",
28
+ "model.layers.10.self_attn.o_proj.weight": "language_model.model.layers.10.self_attn.o_proj.weight",
29
+ "model.layers.10.self_attn.q_proj.weight": "language_model.model.layers.10.self_attn.q_proj.weight",
30
+ "model.layers.10.self_attn.v_proj.weight": "language_model.model.layers.10.self_attn.v_proj.weight",
31
+ "model.layers.11.input_layernorm.weight": "language_model.model.layers.11.input_layernorm.weight",
32
+ "model.layers.11.mlp.down_proj.weight": "language_model.model.layers.11.mlp.down_proj.weight",
33
+ "model.layers.11.mlp.gate_proj.weight": "language_model.model.layers.11.mlp.gate_proj.weight",
34
+ "model.layers.11.mlp.up_proj.weight": "language_model.model.layers.11.mlp.up_proj.weight",
35
+ "model.layers.11.post_attention_layernorm.weight": "language_model.model.layers.11.post_attention_layernorm.weight",
36
+ "model.layers.11.self_attn.k_proj.weight": "language_model.model.layers.11.self_attn.k_proj.weight",
37
+ "model.layers.11.self_attn.o_proj.weight": "language_model.model.layers.11.self_attn.o_proj.weight",
38
+ "model.layers.11.self_attn.q_proj.weight": "language_model.model.layers.11.self_attn.q_proj.weight",
39
+ "model.layers.11.self_attn.v_proj.weight": "language_model.model.layers.11.self_attn.v_proj.weight",
40
+ "model.layers.12.input_layernorm.weight": "language_model.model.layers.12.input_layernorm.weight",
41
+ "model.layers.12.mlp.down_proj.weight": "language_model.model.layers.12.mlp.down_proj.weight",
42
+ "model.layers.12.mlp.gate_proj.weight": "language_model.model.layers.12.mlp.gate_proj.weight",
43
+ "model.layers.12.mlp.up_proj.weight": "language_model.model.layers.12.mlp.up_proj.weight",
44
+ "model.layers.12.post_attention_layernorm.weight": "language_model.model.layers.12.post_attention_layernorm.weight",
45
+ "model.layers.12.self_attn.k_proj.weight": "language_model.model.layers.12.self_attn.k_proj.weight",
46
+ "model.layers.12.self_attn.o_proj.weight": "language_model.model.layers.12.self_attn.o_proj.weight",
47
+ "model.layers.12.self_attn.q_proj.weight": "language_model.model.layers.12.self_attn.q_proj.weight",
48
+ "model.layers.12.self_attn.v_proj.weight": "language_model.model.layers.12.self_attn.v_proj.weight",
49
+ "model.layers.13.input_layernorm.weight": "language_model.model.layers.13.input_layernorm.weight",
50
+ "model.layers.13.mlp.down_proj.weight": "language_model.model.layers.13.mlp.down_proj.weight",
51
+ "model.layers.13.mlp.gate_proj.weight": "language_model.model.layers.13.mlp.gate_proj.weight",
52
+ "model.layers.13.mlp.up_proj.weight": "language_model.model.layers.13.mlp.up_proj.weight",
53
+ "model.layers.13.post_attention_layernorm.weight": "language_model.model.layers.13.post_attention_layernorm.weight",
54
+ "model.layers.13.self_attn.k_proj.weight": "language_model.model.layers.13.self_attn.k_proj.weight",
55
+ "model.layers.13.self_attn.o_proj.weight": "language_model.model.layers.13.self_attn.o_proj.weight",
56
+ "model.layers.13.self_attn.q_proj.weight": "language_model.model.layers.13.self_attn.q_proj.weight",
57
+ "model.layers.13.self_attn.v_proj.weight": "language_model.model.layers.13.self_attn.v_proj.weight",
58
+ "model.layers.14.input_layernorm.weight": "language_model.model.layers.14.input_layernorm.weight",
59
+ "model.layers.14.mlp.down_proj.weight": "language_model.model.layers.14.mlp.down_proj.weight",
60
+ "model.layers.14.mlp.gate_proj.weight": "language_model.model.layers.14.mlp.gate_proj.weight",
61
+ "model.layers.14.mlp.up_proj.weight": "language_model.model.layers.14.mlp.up_proj.weight",
62
+ "model.layers.14.post_attention_layernorm.weight": "language_model.model.layers.14.post_attention_layernorm.weight",
63
+ "model.layers.14.self_attn.k_proj.weight": "language_model.model.layers.14.self_attn.k_proj.weight",
64
+ "model.layers.14.self_attn.o_proj.weight": "language_model.model.layers.14.self_attn.o_proj.weight",
65
+ "model.layers.14.self_attn.q_proj.weight": "language_model.model.layers.14.self_attn.q_proj.weight",
66
+ "model.layers.14.self_attn.v_proj.weight": "language_model.model.layers.14.self_attn.v_proj.weight",
67
+ "model.layers.15.input_layernorm.weight": "language_model.model.layers.15.input_layernorm.weight",
68
+ "model.layers.15.mlp.down_proj.weight": "language_model.model.layers.15.mlp.down_proj.weight",
69
+ "model.layers.15.mlp.gate_proj.weight": "language_model.model.layers.15.mlp.gate_proj.weight",
70
+ "model.layers.15.mlp.up_proj.weight": "language_model.model.layers.15.mlp.up_proj.weight",
71
+ "model.layers.15.post_attention_layernorm.weight": "language_model.model.layers.15.post_attention_layernorm.weight",
72
+ "model.layers.15.self_attn.k_proj.weight": "language_model.model.layers.15.self_attn.k_proj.weight",
73
+ "model.layers.15.self_attn.o_proj.weight": "language_model.model.layers.15.self_attn.o_proj.weight",
74
+ "model.layers.15.self_attn.q_proj.weight": "language_model.model.layers.15.self_attn.q_proj.weight",
75
+ "model.layers.15.self_attn.v_proj.weight": "language_model.model.layers.15.self_attn.v_proj.weight",
76
+ "model.layers.16.input_layernorm.weight": "language_model.model.layers.16.input_layernorm.weight",
77
+ "model.layers.16.mlp.down_proj.weight": "language_model.model.layers.16.mlp.down_proj.weight",
78
+ "model.layers.16.mlp.gate_proj.weight": "language_model.model.layers.16.mlp.gate_proj.weight",
79
+ "model.layers.16.mlp.up_proj.weight": "language_model.model.layers.16.mlp.up_proj.weight",
80
+ "model.layers.16.post_attention_layernorm.weight": "language_model.model.layers.16.post_attention_layernorm.weight",
81
+ "model.layers.16.self_attn.k_proj.weight": "language_model.model.layers.16.self_attn.k_proj.weight",
82
+ "model.layers.16.self_attn.o_proj.weight": "language_model.model.layers.16.self_attn.o_proj.weight",
83
+ "model.layers.16.self_attn.q_proj.weight": "language_model.model.layers.16.self_attn.q_proj.weight",
84
+ "model.layers.16.self_attn.v_proj.weight": "language_model.model.layers.16.self_attn.v_proj.weight",
85
+ "model.layers.17.input_layernorm.weight": "language_model.model.layers.17.input_layernorm.weight",
86
+ "model.layers.17.mlp.down_proj.weight": "language_model.model.layers.17.mlp.down_proj.weight",
87
+ "model.layers.17.mlp.gate_proj.weight": "language_model.model.layers.17.mlp.gate_proj.weight",
88
+ "model.layers.17.mlp.up_proj.weight": "language_model.model.layers.17.mlp.up_proj.weight",
89
+ "model.layers.17.post_attention_layernorm.weight": "language_model.model.layers.17.post_attention_layernorm.weight",
90
+ "model.layers.17.self_attn.k_proj.weight": "language_model.model.layers.17.self_attn.k_proj.weight",
91
+ "model.layers.17.self_attn.o_proj.weight": "language_model.model.layers.17.self_attn.o_proj.weight",
92
+ "model.layers.17.self_attn.q_proj.weight": "language_model.model.layers.17.self_attn.q_proj.weight",
93
+ "model.layers.17.self_attn.v_proj.weight": "language_model.model.layers.17.self_attn.v_proj.weight",
94
+ "model.layers.18.input_layernorm.weight": "language_model.model.layers.18.input_layernorm.weight",
95
+ "model.layers.18.mlp.down_proj.weight": "language_model.model.layers.18.mlp.down_proj.weight",
96
+ "model.layers.18.mlp.gate_proj.weight": "language_model.model.layers.18.mlp.gate_proj.weight",
97
+ "model.layers.18.mlp.up_proj.weight": "language_model.model.layers.18.mlp.up_proj.weight",
98
+ "model.layers.18.post_attention_layernorm.weight": "language_model.model.layers.18.post_attention_layernorm.weight",
99
+ "model.layers.18.self_attn.k_proj.weight": "language_model.model.layers.18.self_attn.k_proj.weight",
100
+ "model.layers.18.self_attn.o_proj.weight": "language_model.model.layers.18.self_attn.o_proj.weight",
101
+ "model.layers.18.self_attn.q_proj.weight": "language_model.model.layers.18.self_attn.q_proj.weight",
102
+ "model.layers.18.self_attn.v_proj.weight": "language_model.model.layers.18.self_attn.v_proj.weight",
103
+ "model.layers.19.input_layernorm.weight": "language_model.model.layers.19.input_layernorm.weight",
104
+ "model.layers.19.mlp.down_proj.weight": "language_model.model.layers.19.mlp.down_proj.weight",
105
+ "model.layers.19.mlp.gate_proj.weight": "language_model.model.layers.19.mlp.gate_proj.weight",
106
+ "model.layers.19.mlp.up_proj.weight": "language_model.model.layers.19.mlp.up_proj.weight",
107
+ "model.layers.19.post_attention_layernorm.weight": "language_model.model.layers.19.post_attention_layernorm.weight",
108
+ "model.layers.19.self_attn.k_proj.weight": "language_model.model.layers.19.self_attn.k_proj.weight",
109
+ "model.layers.19.self_attn.o_proj.weight": "language_model.model.layers.19.self_attn.o_proj.weight",
110
+ "model.layers.19.self_attn.q_proj.weight": "language_model.model.layers.19.self_attn.q_proj.weight",
111
+ "model.layers.19.self_attn.v_proj.weight": "language_model.model.layers.19.self_attn.v_proj.weight",
112
+ "model.layers.2.input_layernorm.weight": "language_model.model.layers.2.input_layernorm.weight",
113
+ "model.layers.2.mlp.down_proj.weight": "language_model.model.layers.2.mlp.down_proj.weight",
114
+ "model.layers.2.mlp.gate_proj.weight": "language_model.model.layers.2.mlp.gate_proj.weight",
115
+ "model.layers.2.mlp.up_proj.weight": "language_model.model.layers.2.mlp.up_proj.weight",
116
+ "model.layers.2.post_attention_layernorm.weight": "language_model.model.layers.2.post_attention_layernorm.weight",
117
+ "model.layers.2.self_attn.k_proj.weight": "language_model.model.layers.2.self_attn.k_proj.weight",
118
+ "model.layers.2.self_attn.o_proj.weight": "language_model.model.layers.2.self_attn.o_proj.weight",
119
+ "model.layers.2.self_attn.q_proj.weight": "language_model.model.layers.2.self_attn.q_proj.weight",
120
+ "model.layers.2.self_attn.v_proj.weight": "language_model.model.layers.2.self_attn.v_proj.weight",
121
+ "model.layers.20.input_layernorm.weight": "language_model.model.layers.20.input_layernorm.weight",
122
+ "model.layers.20.mlp.down_proj.weight": "language_model.model.layers.20.mlp.down_proj.weight",
123
+ "model.layers.20.mlp.gate_proj.weight": "language_model.model.layers.20.mlp.gate_proj.weight",
124
+ "model.layers.20.mlp.up_proj.weight": "language_model.model.layers.20.mlp.up_proj.weight",
125
+ "model.layers.20.post_attention_layernorm.weight": "language_model.model.layers.20.post_attention_layernorm.weight",
126
+ "model.layers.20.self_attn.k_proj.weight": "language_model.model.layers.20.self_attn.k_proj.weight",
127
+ "model.layers.20.self_attn.o_proj.weight": "language_model.model.layers.20.self_attn.o_proj.weight",
128
+ "model.layers.20.self_attn.q_proj.weight": "language_model.model.layers.20.self_attn.q_proj.weight",
129
+ "model.layers.20.self_attn.v_proj.weight": "language_model.model.layers.20.self_attn.v_proj.weight",
130
+ "model.layers.21.input_layernorm.weight": "language_model.model.layers.21.input_layernorm.weight",
131
+ "model.layers.21.mlp.down_proj.weight": "language_model.model.layers.21.mlp.down_proj.weight",
132
+ "model.layers.21.mlp.gate_proj.weight": "language_model.model.layers.21.mlp.gate_proj.weight",
133
+ "model.layers.21.mlp.up_proj.weight": "language_model.model.layers.21.mlp.up_proj.weight",
134
+ "model.layers.21.post_attention_layernorm.weight": "language_model.model.layers.21.post_attention_layernorm.weight",
135
+ "model.layers.21.self_attn.k_proj.weight": "language_model.model.layers.21.self_attn.k_proj.weight",
136
+ "model.layers.21.self_attn.o_proj.weight": "language_model.model.layers.21.self_attn.o_proj.weight",
137
+ "model.layers.21.self_attn.q_proj.weight": "language_model.model.layers.21.self_attn.q_proj.weight",
138
+ "model.layers.21.self_attn.v_proj.weight": "language_model.model.layers.21.self_attn.v_proj.weight",
139
+ "model.layers.22.input_layernorm.weight": "language_model.model.layers.22.input_layernorm.weight",
140
+ "model.layers.22.mlp.down_proj.weight": "language_model.model.layers.22.mlp.down_proj.weight",
141
+ "model.layers.22.mlp.gate_proj.weight": "language_model.model.layers.22.mlp.gate_proj.weight",
142
+ "model.layers.22.mlp.up_proj.weight": "language_model.model.layers.22.mlp.up_proj.weight",
143
+ "model.layers.22.post_attention_layernorm.weight": "language_model.model.layers.22.post_attention_layernorm.weight",
144
+ "model.layers.22.self_attn.k_proj.weight": "language_model.model.layers.22.self_attn.k_proj.weight",
145
+ "model.layers.22.self_attn.o_proj.weight": "language_model.model.layers.22.self_attn.o_proj.weight",
146
+ "model.layers.22.self_attn.q_proj.weight": "language_model.model.layers.22.self_attn.q_proj.weight",
147
+ "model.layers.22.self_attn.v_proj.weight": "language_model.model.layers.22.self_attn.v_proj.weight",
148
+ "model.layers.23.input_layernorm.weight": "language_model.model.layers.23.input_layernorm.weight",
149
+ "model.layers.23.mlp.down_proj.weight": "language_model.model.layers.23.mlp.down_proj.weight",
150
+ "model.layers.23.mlp.gate_proj.weight": "language_model.model.layers.23.mlp.gate_proj.weight",
151
+ "model.layers.23.mlp.up_proj.weight": "language_model.model.layers.23.mlp.up_proj.weight",
152
+ "model.layers.23.post_attention_layernorm.weight": "language_model.model.layers.23.post_attention_layernorm.weight",
153
+ "model.layers.23.self_attn.k_proj.weight": "language_model.model.layers.23.self_attn.k_proj.weight",
154
+ "model.layers.23.self_attn.o_proj.weight": "language_model.model.layers.23.self_attn.o_proj.weight",
155
+ "model.layers.23.self_attn.q_proj.weight": "language_model.model.layers.23.self_attn.q_proj.weight",
156
+ "model.layers.23.self_attn.v_proj.weight": "language_model.model.layers.23.self_attn.v_proj.weight",
157
+ "model.layers.24.input_layernorm.weight": "language_model.model.layers.24.input_layernorm.weight",
158
+ "model.layers.24.mlp.down_proj.weight": "language_model.model.layers.24.mlp.down_proj.weight",
159
+ "model.layers.24.mlp.gate_proj.weight": "language_model.model.layers.24.mlp.gate_proj.weight",
160
+ "model.layers.24.mlp.up_proj.weight": "language_model.model.layers.24.mlp.up_proj.weight",
161
+ "model.layers.24.post_attention_layernorm.weight": "language_model.model.layers.24.post_attention_layernorm.weight",
162
+ "model.layers.24.self_attn.k_proj.weight": "language_model.model.layers.24.self_attn.k_proj.weight",
163
+ "model.layers.24.self_attn.o_proj.weight": "language_model.model.layers.24.self_attn.o_proj.weight",
164
+ "model.layers.24.self_attn.q_proj.weight": "language_model.model.layers.24.self_attn.q_proj.weight",
165
+ "model.layers.24.self_attn.v_proj.weight": "language_model.model.layers.24.self_attn.v_proj.weight",
166
+ "model.layers.25.input_layernorm.weight": "language_model.model.layers.25.input_layernorm.weight",
167
+ "model.layers.25.mlp.down_proj.weight": "language_model.model.layers.25.mlp.down_proj.weight",
168
+ "model.layers.25.mlp.gate_proj.weight": "language_model.model.layers.25.mlp.gate_proj.weight",
169
+ "model.layers.25.mlp.up_proj.weight": "language_model.model.layers.25.mlp.up_proj.weight",
170
+ "model.layers.25.post_attention_layernorm.weight": "language_model.model.layers.25.post_attention_layernorm.weight",
171
+ "model.layers.25.self_attn.k_proj.weight": "language_model.model.layers.25.self_attn.k_proj.weight",
172
+ "model.layers.25.self_attn.o_proj.weight": "language_model.model.layers.25.self_attn.o_proj.weight",
173
+ "model.layers.25.self_attn.q_proj.weight": "language_model.model.layers.25.self_attn.q_proj.weight",
174
+ "model.layers.25.self_attn.v_proj.weight": "language_model.model.layers.25.self_attn.v_proj.weight",
175
+ "model.layers.26.input_layernorm.weight": "language_model.model.layers.26.input_layernorm.weight",
176
+ "model.layers.26.mlp.down_proj.weight": "language_model.model.layers.26.mlp.down_proj.weight",
177
+ "model.layers.26.mlp.gate_proj.weight": "language_model.model.layers.26.mlp.gate_proj.weight",
178
+ "model.layers.26.mlp.up_proj.weight": "language_model.model.layers.26.mlp.up_proj.weight",
179
+ "model.layers.26.post_attention_layernorm.weight": "language_model.model.layers.26.post_attention_layernorm.weight",
180
+ "model.layers.26.self_attn.k_proj.weight": "language_model.model.layers.26.self_attn.k_proj.weight",
181
+ "model.layers.26.self_attn.o_proj.weight": "language_model.model.layers.26.self_attn.o_proj.weight",
182
+ "model.layers.26.self_attn.q_proj.weight": "language_model.model.layers.26.self_attn.q_proj.weight",
183
+ "model.layers.26.self_attn.v_proj.weight": "language_model.model.layers.26.self_attn.v_proj.weight",
184
+ "model.layers.27.input_layernorm.weight": "language_model.model.layers.27.input_layernorm.weight",
185
+ "model.layers.27.mlp.down_proj.weight": "language_model.model.layers.27.mlp.down_proj.weight",
186
+ "model.layers.27.mlp.gate_proj.weight": "language_model.model.layers.27.mlp.gate_proj.weight",
187
+ "model.layers.27.mlp.up_proj.weight": "language_model.model.layers.27.mlp.up_proj.weight",
188
+ "model.layers.27.post_attention_layernorm.weight": "language_model.model.layers.27.post_attention_layernorm.weight",
189
+ "model.layers.27.self_attn.k_proj.weight": "language_model.model.layers.27.self_attn.k_proj.weight",
190
+ "model.layers.27.self_attn.o_proj.weight": "language_model.model.layers.27.self_attn.o_proj.weight",
191
+ "model.layers.27.self_attn.q_proj.weight": "language_model.model.layers.27.self_attn.q_proj.weight",
192
+ "model.layers.27.self_attn.v_proj.weight": "language_model.model.layers.27.self_attn.v_proj.weight",
193
+ "model.layers.28.input_layernorm.weight": "language_model.model.layers.28.input_layernorm.weight",
194
+ "model.layers.28.mlp.down_proj.weight": "language_model.model.layers.28.mlp.down_proj.weight",
195
+ "model.layers.28.mlp.gate_proj.weight": "language_model.model.layers.28.mlp.gate_proj.weight",
196
+ "model.layers.28.mlp.up_proj.weight": "language_model.model.layers.28.mlp.up_proj.weight",
197
+ "model.layers.28.post_attention_layernorm.weight": "language_model.model.layers.28.post_attention_layernorm.weight",
198
+ "model.layers.28.self_attn.k_proj.weight": "language_model.model.layers.28.self_attn.k_proj.weight",
199
+ "model.layers.28.self_attn.o_proj.weight": "language_model.model.layers.28.self_attn.o_proj.weight",
200
+ "model.layers.28.self_attn.q_proj.weight": "language_model.model.layers.28.self_attn.q_proj.weight",
201
+ "model.layers.28.self_attn.v_proj.weight": "language_model.model.layers.28.self_attn.v_proj.weight",
202
+ "model.layers.29.input_layernorm.weight": "language_model.model.layers.29.input_layernorm.weight",
203
+ "model.layers.29.mlp.down_proj.weight": "language_model.model.layers.29.mlp.down_proj.weight",
204
+ "model.layers.29.mlp.gate_proj.weight": "language_model.model.layers.29.mlp.gate_proj.weight",
205
+ "model.layers.29.mlp.up_proj.weight": "language_model.model.layers.29.mlp.up_proj.weight",
206
+ "model.layers.29.post_attention_layernorm.weight": "language_model.model.layers.29.post_attention_layernorm.weight",
207
+ "model.layers.29.self_attn.k_proj.weight": "language_model.model.layers.29.self_attn.k_proj.weight",
208
+ "model.layers.29.self_attn.o_proj.weight": "language_model.model.layers.29.self_attn.o_proj.weight",
209
+ "model.layers.29.self_attn.q_proj.weight": "language_model.model.layers.29.self_attn.q_proj.weight",
210
+ "model.layers.29.self_attn.v_proj.weight": "language_model.model.layers.29.self_attn.v_proj.weight",
211
+ "model.layers.3.input_layernorm.weight": "language_model.model.layers.3.input_layernorm.weight",
212
+ "model.layers.3.mlp.down_proj.weight": "language_model.model.layers.3.mlp.down_proj.weight",
213
+ "model.layers.3.mlp.gate_proj.weight": "language_model.model.layers.3.mlp.gate_proj.weight",
214
+ "model.layers.3.mlp.up_proj.weight": "language_model.model.layers.3.mlp.up_proj.weight",
215
+ "model.layers.3.post_attention_layernorm.weight": "language_model.model.layers.3.post_attention_layernorm.weight",
216
+ "model.layers.3.self_attn.k_proj.weight": "language_model.model.layers.3.self_attn.k_proj.weight",
217
+ "model.layers.3.self_attn.o_proj.weight": "language_model.model.layers.3.self_attn.o_proj.weight",
218
+ "model.layers.3.self_attn.q_proj.weight": "language_model.model.layers.3.self_attn.q_proj.weight",
219
+ "model.layers.3.self_attn.v_proj.weight": "language_model.model.layers.3.self_attn.v_proj.weight",
220
+ "model.layers.30.input_layernorm.weight": "language_model.model.layers.30.input_layernorm.weight",
221
+ "model.layers.30.mlp.down_proj.weight": "language_model.model.layers.30.mlp.down_proj.weight",
222
+ "model.layers.30.mlp.gate_proj.weight": "language_model.model.layers.30.mlp.gate_proj.weight",
223
+ "model.layers.30.mlp.up_proj.weight": "language_model.model.layers.30.mlp.up_proj.weight",
224
+ "model.layers.30.post_attention_layernorm.weight": "language_model.model.layers.30.post_attention_layernorm.weight",
225
+ "model.layers.30.self_attn.k_proj.weight": "language_model.model.layers.30.self_attn.k_proj.weight",
226
+ "model.layers.30.self_attn.o_proj.weight": "language_model.model.layers.30.self_attn.o_proj.weight",
227
+ "model.layers.30.self_attn.q_proj.weight": "language_model.model.layers.30.self_attn.q_proj.weight",
228
+ "model.layers.30.self_attn.v_proj.weight": "language_model.model.layers.30.self_attn.v_proj.weight",
229
+ "model.layers.31.input_layernorm.weight": "language_model.model.layers.31.input_layernorm.weight",
230
+ "model.layers.31.mlp.down_proj.weight": "language_model.model.layers.31.mlp.down_proj.weight",
231
+ "model.layers.31.mlp.gate_proj.weight": "language_model.model.layers.31.mlp.gate_proj.weight",
232
+ "model.layers.31.mlp.up_proj.weight": "language_model.model.layers.31.mlp.up_proj.weight",
233
+ "model.layers.31.post_attention_layernorm.weight": "language_model.model.layers.31.post_attention_layernorm.weight",
234
+ "model.layers.31.self_attn.k_proj.weight": "language_model.model.layers.31.self_attn.k_proj.weight",
235
+ "model.layers.31.self_attn.o_proj.weight": "language_model.model.layers.31.self_attn.o_proj.weight",
236
+ "model.layers.31.self_attn.q_proj.weight": "language_model.model.layers.31.self_attn.q_proj.weight",
237
+ "model.layers.31.self_attn.v_proj.weight": "language_model.model.layers.31.self_attn.v_proj.weight",
238
+ "model.layers.32.input_layernorm.weight": "language_model.model.layers.32.input_layernorm.weight",
239
+ "model.layers.32.mlp.down_proj.weight": "language_model.model.layers.32.mlp.down_proj.weight",
240
+ "model.layers.32.mlp.gate_proj.weight": "language_model.model.layers.32.mlp.gate_proj.weight",
241
+ "model.layers.32.mlp.up_proj.weight": "language_model.model.layers.32.mlp.up_proj.weight",
242
+ "model.layers.32.post_attention_layernorm.weight": "language_model.model.layers.32.post_attention_layernorm.weight",
243
+ "model.layers.32.self_attn.k_proj.weight": "language_model.model.layers.32.self_attn.k_proj.weight",
244
+ "model.layers.32.self_attn.o_proj.weight": "language_model.model.layers.32.self_attn.o_proj.weight",
245
+ "model.layers.32.self_attn.q_proj.weight": "language_model.model.layers.32.self_attn.q_proj.weight",
246
+ "model.layers.32.self_attn.v_proj.weight": "language_model.model.layers.32.self_attn.v_proj.weight",
247
+ "model.layers.33.input_layernorm.weight": "language_model.model.layers.33.input_layernorm.weight",
248
+ "model.layers.33.mlp.down_proj.weight": "language_model.model.layers.33.mlp.down_proj.weight",
249
+ "model.layers.33.mlp.gate_proj.weight": "language_model.model.layers.33.mlp.gate_proj.weight",
250
+ "model.layers.33.mlp.up_proj.weight": "language_model.model.layers.33.mlp.up_proj.weight",
251
+ "model.layers.33.post_attention_layernorm.weight": "language_model.model.layers.33.post_attention_layernorm.weight",
252
+ "model.layers.33.self_attn.k_proj.weight": "language_model.model.layers.33.self_attn.k_proj.weight",
253
+ "model.layers.33.self_attn.o_proj.weight": "language_model.model.layers.33.self_attn.o_proj.weight",
254
+ "model.layers.33.self_attn.q_proj.weight": "language_model.model.layers.33.self_attn.q_proj.weight",
255
+ "model.layers.33.self_attn.v_proj.weight": "language_model.model.layers.33.self_attn.v_proj.weight",
256
+ "model.layers.34.input_layernorm.weight": "language_model.model.layers.34.input_layernorm.weight",
257
+ "model.layers.34.mlp.down_proj.weight": "language_model.model.layers.34.mlp.down_proj.weight",
258
+ "model.layers.34.mlp.gate_proj.weight": "language_model.model.layers.34.mlp.gate_proj.weight",
259
+ "model.layers.34.mlp.up_proj.weight": "language_model.model.layers.34.mlp.up_proj.weight",
260
+ "model.layers.34.post_attention_layernorm.weight": "language_model.model.layers.34.post_attention_layernorm.weight",
261
+ "model.layers.34.self_attn.k_proj.weight": "language_model.model.layers.34.self_attn.k_proj.weight",
262
+ "model.layers.34.self_attn.o_proj.weight": "language_model.model.layers.34.self_attn.o_proj.weight",
263
+ "model.layers.34.self_attn.q_proj.weight": "language_model.model.layers.34.self_attn.q_proj.weight",
264
+ "model.layers.34.self_attn.v_proj.weight": "language_model.model.layers.34.self_attn.v_proj.weight",
265
+ "model.layers.35.input_layernorm.weight": "language_model.model.layers.35.input_layernorm.weight",
266
+ "model.layers.35.mlp.down_proj.weight": "language_model.model.layers.35.mlp.down_proj.weight",
267
+ "model.layers.35.mlp.gate_proj.weight": "language_model.model.layers.35.mlp.gate_proj.weight",
268
+ "model.layers.35.mlp.up_proj.weight": "language_model.model.layers.35.mlp.up_proj.weight",
269
+ "model.layers.35.post_attention_layernorm.weight": "language_model.model.layers.35.post_attention_layernorm.weight",
270
+ "model.layers.35.self_attn.k_proj.weight": "language_model.model.layers.35.self_attn.k_proj.weight",
271
+ "model.layers.35.self_attn.o_proj.weight": "language_model.model.layers.35.self_attn.o_proj.weight",
272
+ "model.layers.35.self_attn.q_proj.weight": "language_model.model.layers.35.self_attn.q_proj.weight",
273
+ "model.layers.35.self_attn.v_proj.weight": "language_model.model.layers.35.self_attn.v_proj.weight",
274
+ "model.layers.36.input_layernorm.weight": "language_model.model.layers.36.input_layernorm.weight",
275
+ "model.layers.36.mlp.down_proj.weight": "language_model.model.layers.36.mlp.down_proj.weight",
276
+ "model.layers.36.mlp.gate_proj.weight": "language_model.model.layers.36.mlp.gate_proj.weight",
277
+ "model.layers.36.mlp.up_proj.weight": "language_model.model.layers.36.mlp.up_proj.weight",
278
+ "model.layers.36.post_attention_layernorm.weight": "language_model.model.layers.36.post_attention_layernorm.weight",
279
+ "model.layers.36.self_attn.k_proj.weight": "language_model.model.layers.36.self_attn.k_proj.weight",
280
+ "model.layers.36.self_attn.o_proj.weight": "language_model.model.layers.36.self_attn.o_proj.weight",
281
+ "model.layers.36.self_attn.q_proj.weight": "language_model.model.layers.36.self_attn.q_proj.weight",
282
+ "model.layers.36.self_attn.v_proj.weight": "language_model.model.layers.36.self_attn.v_proj.weight",
283
+ "model.layers.37.input_layernorm.weight": "language_model.model.layers.37.input_layernorm.weight",
284
+ "model.layers.37.mlp.down_proj.weight": "language_model.model.layers.37.mlp.down_proj.weight",
285
+ "model.layers.37.mlp.gate_proj.weight": "language_model.model.layers.37.mlp.gate_proj.weight",
286
+ "model.layers.37.mlp.up_proj.weight": "language_model.model.layers.37.mlp.up_proj.weight",
287
+ "model.layers.37.post_attention_layernorm.weight": "language_model.model.layers.37.post_attention_layernorm.weight",
288
+ "model.layers.37.self_attn.k_proj.weight": "language_model.model.layers.37.self_attn.k_proj.weight",
289
+ "model.layers.37.self_attn.o_proj.weight": "language_model.model.layers.37.self_attn.o_proj.weight",
290
+ "model.layers.37.self_attn.q_proj.weight": "language_model.model.layers.37.self_attn.q_proj.weight",
291
+ "model.layers.37.self_attn.v_proj.weight": "language_model.model.layers.37.self_attn.v_proj.weight",
292
+ "model.layers.38.input_layernorm.weight": "language_model.model.layers.38.input_layernorm.weight",
293
+ "model.layers.38.mlp.down_proj.weight": "language_model.model.layers.38.mlp.down_proj.weight",
294
+ "model.layers.38.mlp.gate_proj.weight": "language_model.model.layers.38.mlp.gate_proj.weight",
295
+ "model.layers.38.mlp.up_proj.weight": "language_model.model.layers.38.mlp.up_proj.weight",
296
+ "model.layers.38.post_attention_layernorm.weight": "language_model.model.layers.38.post_attention_layernorm.weight",
297
+ "model.layers.38.self_attn.k_proj.weight": "language_model.model.layers.38.self_attn.k_proj.weight",
298
+ "model.layers.38.self_attn.o_proj.weight": "language_model.model.layers.38.self_attn.o_proj.weight",
299
+ "model.layers.38.self_attn.q_proj.weight": "language_model.model.layers.38.self_attn.q_proj.weight",
300
+ "model.layers.38.self_attn.v_proj.weight": "language_model.model.layers.38.self_attn.v_proj.weight",
301
+ "model.layers.39.input_layernorm.weight": "language_model.model.layers.39.input_layernorm.weight",
302
+ "model.layers.39.mlp.down_proj.weight": "language_model.model.layers.39.mlp.down_proj.weight",
303
+ "model.layers.39.mlp.gate_proj.weight": "language_model.model.layers.39.mlp.gate_proj.weight",
304
+ "model.layers.39.mlp.up_proj.weight": "language_model.model.layers.39.mlp.up_proj.weight",
305
+ "model.layers.39.post_attention_layernorm.weight": "language_model.model.layers.39.post_attention_layernorm.weight",
306
+ "model.layers.39.self_attn.k_proj.weight": "language_model.model.layers.39.self_attn.k_proj.weight",
307
+ "model.layers.39.self_attn.o_proj.weight": "language_model.model.layers.39.self_attn.o_proj.weight",
308
+ "model.layers.39.self_attn.q_proj.weight": "language_model.model.layers.39.self_attn.q_proj.weight",
309
+ "model.layers.39.self_attn.v_proj.weight": "language_model.model.layers.39.self_attn.v_proj.weight",
310
+ "model.layers.4.input_layernorm.weight": "language_model.model.layers.4.input_layernorm.weight",
311
+ "model.layers.4.mlp.down_proj.weight": "language_model.model.layers.4.mlp.down_proj.weight",
312
+ "model.layers.4.mlp.gate_proj.weight": "language_model.model.layers.4.mlp.gate_proj.weight",
313
+ "model.layers.4.mlp.up_proj.weight": "language_model.model.layers.4.mlp.up_proj.weight",
314
+ "model.layers.4.post_attention_layernorm.weight": "language_model.model.layers.4.post_attention_layernorm.weight",
315
+ "model.layers.4.self_attn.k_proj.weight": "language_model.model.layers.4.self_attn.k_proj.weight",
316
+ "model.layers.4.self_attn.o_proj.weight": "language_model.model.layers.4.self_attn.o_proj.weight",
317
+ "model.layers.4.self_attn.q_proj.weight": "language_model.model.layers.4.self_attn.q_proj.weight",
318
+ "model.layers.4.self_attn.v_proj.weight": "language_model.model.layers.4.self_attn.v_proj.weight",
319
+ "model.layers.5.input_layernorm.weight": "language_model.model.layers.5.input_layernorm.weight",
320
+ "model.layers.5.mlp.down_proj.weight": "language_model.model.layers.5.mlp.down_proj.weight",
321
+ "model.layers.5.mlp.gate_proj.weight": "language_model.model.layers.5.mlp.gate_proj.weight",
322
+ "model.layers.5.mlp.up_proj.weight": "language_model.model.layers.5.mlp.up_proj.weight",
323
+ "model.layers.5.post_attention_layernorm.weight": "language_model.model.layers.5.post_attention_layernorm.weight",
324
+ "model.layers.5.self_attn.k_proj.weight": "language_model.model.layers.5.self_attn.k_proj.weight",
325
+ "model.layers.5.self_attn.o_proj.weight": "language_model.model.layers.5.self_attn.o_proj.weight",
326
+ "model.layers.5.self_attn.q_proj.weight": "language_model.model.layers.5.self_attn.q_proj.weight",
327
+ "model.layers.5.self_attn.v_proj.weight": "language_model.model.layers.5.self_attn.v_proj.weight",
328
+ "model.layers.6.input_layernorm.weight": "language_model.model.layers.6.input_layernorm.weight",
329
+ "model.layers.6.mlp.down_proj.weight": "language_model.model.layers.6.mlp.down_proj.weight",
330
+ "model.layers.6.mlp.gate_proj.weight": "language_model.model.layers.6.mlp.gate_proj.weight",
331
+ "model.layers.6.mlp.up_proj.weight": "language_model.model.layers.6.mlp.up_proj.weight",
332
+ "model.layers.6.post_attention_layernorm.weight": "language_model.model.layers.6.post_attention_layernorm.weight",
333
+ "model.layers.6.self_attn.k_proj.weight": "language_model.model.layers.6.self_attn.k_proj.weight",
334
+ "model.layers.6.self_attn.o_proj.weight": "language_model.model.layers.6.self_attn.o_proj.weight",
335
+ "model.layers.6.self_attn.q_proj.weight": "language_model.model.layers.6.self_attn.q_proj.weight",
336
+ "model.layers.6.self_attn.v_proj.weight": "language_model.model.layers.6.self_attn.v_proj.weight",
337
+ "model.layers.7.input_layernorm.weight": "language_model.model.layers.7.input_layernorm.weight",
338
+ "model.layers.7.mlp.down_proj.weight": "language_model.model.layers.7.mlp.down_proj.weight",
339
+ "model.layers.7.mlp.gate_proj.weight": "language_model.model.layers.7.mlp.gate_proj.weight",
340
+ "model.layers.7.mlp.up_proj.weight": "language_model.model.layers.7.mlp.up_proj.weight",
341
+ "model.layers.7.post_attention_layernorm.weight": "language_model.model.layers.7.post_attention_layernorm.weight",
342
+ "model.layers.7.self_attn.k_proj.weight": "language_model.model.layers.7.self_attn.k_proj.weight",
343
+ "model.layers.7.self_attn.o_proj.weight": "language_model.model.layers.7.self_attn.o_proj.weight",
344
+ "model.layers.7.self_attn.q_proj.weight": "language_model.model.layers.7.self_attn.q_proj.weight",
345
+ "model.layers.7.self_attn.v_proj.weight": "language_model.model.layers.7.self_attn.v_proj.weight",
346
+ "model.layers.8.input_layernorm.weight": "language_model.model.layers.8.input_layernorm.weight",
347
+ "model.layers.8.mlp.down_proj.weight": "language_model.model.layers.8.mlp.down_proj.weight",
348
+ "model.layers.8.mlp.gate_proj.weight": "language_model.model.layers.8.mlp.gate_proj.weight",
349
+ "model.layers.8.mlp.up_proj.weight": "language_model.model.layers.8.mlp.up_proj.weight",
350
+ "model.layers.8.post_attention_layernorm.weight": "language_model.model.layers.8.post_attention_layernorm.weight",
351
+ "model.layers.8.self_attn.k_proj.weight": "language_model.model.layers.8.self_attn.k_proj.weight",
352
+ "model.layers.8.self_attn.o_proj.weight": "language_model.model.layers.8.self_attn.o_proj.weight",
353
+ "model.layers.8.self_attn.q_proj.weight": "language_model.model.layers.8.self_attn.q_proj.weight",
354
+ "model.layers.8.self_attn.v_proj.weight": "language_model.model.layers.8.self_attn.v_proj.weight",
355
+ "model.layers.9.input_layernorm.weight": "language_model.model.layers.9.input_layernorm.weight",
356
+ "model.layers.9.mlp.down_proj.weight": "language_model.model.layers.9.mlp.down_proj.weight",
357
+ "model.layers.9.mlp.gate_proj.weight": "language_model.model.layers.9.mlp.gate_proj.weight",
358
+ "model.layers.9.mlp.up_proj.weight": "language_model.model.layers.9.mlp.up_proj.weight",
359
+ "model.layers.9.post_attention_layernorm.weight": "language_model.model.layers.9.post_attention_layernorm.weight",
360
+ "model.layers.9.self_attn.k_proj.weight": "language_model.model.layers.9.self_attn.k_proj.weight",
361
+ "model.layers.9.self_attn.o_proj.weight": "language_model.model.layers.9.self_attn.o_proj.weight",
362
+ "model.layers.9.self_attn.q_proj.weight": "language_model.model.layers.9.self_attn.q_proj.weight",
363
+ "model.layers.9.self_attn.v_proj.weight": "language_model.model.layers.9.self_attn.v_proj.weight",
364
+ "model.mm_projector.0.bias": "multi_modal_projector.linear_1.bias",
365
+ "model.mm_projector.0.weight": "multi_modal_projector.linear_1.weight",
366
+ "model.mm_projector.2.bias": "multi_modal_projector.linear_2.bias",
367
+ "model.mm_projector.2.weight": "multi_modal_projector.linear_2.weight",
368
+ "model.norm.weight": "language_model.model.norm.weight",
369
+ "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "vision_tower.vision_model.embeddings.class_embedding",
370
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "vision_tower.vision_model.embeddings.patch_embedding.weight",
371
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "vision_tower.vision_model.embeddings.position_embedding.weight",
372
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias",
373
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight",
374
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias",
375
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight",
376
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias",
377
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight",
378
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias",
379
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight",
380
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias",
381
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight",
382
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias",
383
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight",
384
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias",
385
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight",
386
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias",
387
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight",
388
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias",
389
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight",
390
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias",
391
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight",
392
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias",
393
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight",
394
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias",
395
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight",
396
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias",
397
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight",
398
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias",
399
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight",
400
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias",
401
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight",
402
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias",
403
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight",
404
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias",
405
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight",
406
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias",
407
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight",
408
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias",
409
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight",
410
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias",
411
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight",
412
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias",
413
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight",
414
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias",
415
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight",
724
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias",
725
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight",
726
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias",
727
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight",
728
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias",
729
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight",
730
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias",
731
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight",
732
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias",
733
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight",
734
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias",
735
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight",
736
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias",
737
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight",
738
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias",
739
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight",
740
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias",
741
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight",
742
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias",
743
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight",
744
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias",
745
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight",
746
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias",
747
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight",
748
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias",
749
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight",
750
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias",
751
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight",
752
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias",
753
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight",
754
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias",
755
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight",
756
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "vision_tower.vision_model.post_layernorm.bias",
757
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "vision_tower.vision_model.post_layernorm.weight",
758
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "vision_tower.vision_model.pre_layrnorm.bias",
759
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "vision_tower.vision_model.pre_layrnorm.weight"
760
+ }
llava_merged_dpo_13b_1epoch_1iteration/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/yiyang_zhou/workplace/LLaVA/checkpoint/llava-v1.5-13b",
3
+ "architectures": [
4
+ "LlavaLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "freeze_mm_mlp_adapter": false,
11
+ "freeze_mm_vision_resampler": false,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 5120,
14
+ "image_aspect_ratio": "pad",
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 13824,
17
+ "max_length": 4096,
18
+ "max_position_embeddings": 4096,
19
+ "mm_hidden_size": 1024,
20
+ "mm_patch_merge_type": "flat",
21
+ "mm_projector_lr": 2e-05,
22
+ "mm_projector_type": "mlp2x_gelu",
23
+ "mm_resampler_type": null,
24
+ "mm_use_im_patch_token": false,
25
+ "mm_use_im_start_end": false,
26
+ "mm_vision_select_feature": "patch",
27
+ "mm_vision_select_layer": -2,
28
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
29
+ "model_type": "llava_llama",
30
+ "num_attention_heads": 40,
31
+ "num_hidden_layers": 40,
32
+ "num_key_value_heads": 40,
33
+ "pad_token_id": 0,
34
+ "pretraining_tp": 1,
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "tie_word_embeddings": false,
39
+ "tokenizer_model_max_length": 1024,
40
+ "tokenizer_padding_side": "right",
41
+ "torch_dtype": "float16",
42
+ "transformers_version": "4.33.0",
43
+ "tune_mm_mlp_adapter": false,
44
+ "tune_mm_vision_resampler": false,
45
+ "unfreeze_mm_vision_tower": false,
46
+ "use_cache": true,
47
+ "use_mm_proj": true,
48
+ "vocab_size": 32000
49
+ }
llava_merged_dpo_13b_1epoch_1iteration/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.33.0"
8
+ }
llava_merged_dpo_13b_1epoch_1iteration/pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17cfee13735ed56bffa3b4beb23e38234dd0a69f688a38a0214cd7c999b262f3
3
+ size 9948719920
llava_merged_dpo_13b_1epoch_1iteration/pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e649102fe3bf0535475d1545ed9ac5abdf90a3b27fae0f7f4fa1d557b309e2a
3
+ size 9904155895
llava_merged_dpo_13b_1epoch_1iteration/pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b27d216a9d22e3c32c92e038c970daf736ce5f3913290ebefba0a9d64cf4f74
3
+ size 6849078577
llava_merged_dpo_13b_1epoch_1iteration/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,765 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26701678592
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
242
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
243
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
244
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
245
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
246
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
247
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
248
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
249
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
251
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
252
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
253
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
254
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
255
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
256
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
257
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
258
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
259
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
260
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
261
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
262
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
263
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
264
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
265
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
266
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
267
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
268
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
269
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
270
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
271
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
272
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
273
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
274
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
275
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
276
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
277
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
278
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
279
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
280
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
281
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
282
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
283
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
284
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
285
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
286
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
287
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
288
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
289
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
290
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
291
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
292
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
293
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
294
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
295
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
296
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
297
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
298
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
299
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
300
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
301
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
302
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
303
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
304
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
305
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
306
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
307
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
308
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
309
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
310
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
311
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
312
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
313
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
314
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
315
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
316
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
317
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
318
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
319
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
320
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
321
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
322
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
323
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
324
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
325
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
326
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
327
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
328
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
329
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
330
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
331
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
332
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
333
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
334
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
335
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
336
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
337
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
338
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
339
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
340
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
341
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
342
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
343
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
344
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
345
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
346
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
347
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
348
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
349
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
350
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
351
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
352
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
353
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
354
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
355
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
356
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
357
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
358
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
359
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
360
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
361
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
362
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
363
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
364
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
365
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
366
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
367
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
368
+ "model.mm_projector.0.bias": "pytorch_model-00003-of-00003.bin",
369
+ "model.mm_projector.0.weight": "pytorch_model-00003-of-00003.bin",
370
+ "model.mm_projector.2.bias": "pytorch_model-00003-of-00003.bin",
371
+ "model.mm_projector.2.weight": "pytorch_model-00003-of-00003.bin",
372
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin",
373
+ "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00003-of-00003.bin",
374
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00003.bin",
375
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00003-of-00003.bin",
376
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
377
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
378
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
379
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
380
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
381
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
382
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
383
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
384
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
385
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
386
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
387
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
388
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
389
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
390
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
391
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
392
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
393
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
394
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
395
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
396
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
397
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
398
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
399
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
400
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
401
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
402
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
403
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
404
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
405
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
406
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
407
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
408
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
409
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
410
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
411
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
412
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
413
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
414
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
415
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
724
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
725
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
726
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
727
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
728
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
729
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
730
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
731
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
732
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
733
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
734
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
735
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
736
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
737
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
738
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
739
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
740
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
741
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
742
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
743
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
744
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
745
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
746
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
747
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
748
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
749
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
750
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
751
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
752
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
753
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
754
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
755
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
756
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
757
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
758
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
759
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
760
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00003-of-00003.bin",
761
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00003-of-00003.bin",
762
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00003-of-00003.bin",
763
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00003-of-00003.bin"
764
+ }
765
+ }
llava_merged_dpo_13b_1epoch_1iteration/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
llava_merged_dpo_13b_1epoch_1iteration/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
llava_merged_dpo_13b_1epoch_1iteration/tokenizer_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 2048,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "spaces_between_special_tokens": false,
27
+ "tokenizer_class": "LlamaTokenizer",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "use_default_system_prompt": true
37
+ }
my_dataset12k.json ADDED
The diff for this file is too large to render. See raw diff
 
sample.sh ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6 accelerate launch \
3
+ --num_processes=7 \
4
+ --num_machines=1 \
5
+ --gpu_ids=0,1,2,3,4,5,6 \
6
+ --mixed_precision=fp16 \
7
+ --dynamo_backend=no \
8
+ ./sample_tree.py \
9
+ --model-path="/home/yiyangai/Projects/dongjie/StepbyStep/llava_13b_dpoed/llava_merged_dpo_13b_1epoch_1iteration" \
10
+ --dataset_path="/home/yiyangai/Projects/dongjie/LlaVa-Instruct-150k/LLaVA-Instruct-150K/my_dataset12k.json" \
11
+ --images_dir="../LlaVa-Instruct-150k/data/train2014" \
12
+ --output_dir="/home/yiyangai/Projects/dongjie/StepbyStep/Save_Folder/2024-5-9-after1dpo-13b" \
13
+ --weight_mapping_path="/home/yiyangai/Projects/dongjie/5de42962e78a4485afa7a05120d78d88/key_mapping_13b.json" \
14
+
sample_tree.py ADDED
@@ -0,0 +1,340 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from utils import *
2
+ from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN
3
+ from llava.constants import DEFAULT_IMAGE_PATCH_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN
4
+ from llava.conversation import conv_templates, SeparatorStyle
5
+ from llava.model.builder import load_pretrained_model
6
+ from llava.utils import disable_torch_init
7
+ from llava import conversation as conversation_lib
8
+ from llava.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria, process_images
9
+ from llava.model import *
10
+ from transformers import AutoProcessor, CLIPModel
11
+
12
+ from accelerate.utils import gather_object
13
+ import torch
14
+ from transformers import AutoProcessor, LlavaForConditionalGeneration
15
+ from transformers import AutoTokenizer
16
+ import json
17
+ from accelerate import Accelerator
18
+ from PIL import Image
19
+ import torch.nn.functional as F
20
+ import os
21
+ import pickle
22
+
23
+ def get_done_ids(file_path):
24
+ # 初始化一个空列表来存储 id 值
25
+ id_list = []
26
+
27
+ # 打开文件，并逐行读取
28
+ with open(file_path, 'r') as file:
29
+ for line in file:
30
+ # 将每一行的内容从 JSON 字符串转换为字典
31
+ # print(line)
32
+ data = json.loads(line)
33
+ # 将字典中 'id' 键的值添加到列表中
34
+ if 'id' in data:
35
+ id_list.append(data['id'])
36
+ return(id_list)
37
+
38
+
39
+ def save_object(obj, file_path):
40
+ """保存对象到指定的Pickle文件."""
41
+ with open(file_path, 'wb') as file: # 打开文件以二进制写入模式
42
+ pickle.dump(obj, file) # 使用pickle的dump方法将对象序列化到文件
43
+
44
+
45
+ def get_prompts(inputs):
46
+ input_questions = [DEFAULT_IMAGE_TOKEN + '\n' + input_question for input_question in inputs]
47
+
48
+ prompts = []
49
+ for input_q in input_questions:
50
+ conv = conv_templates['v1'].copy()
51
+ conv.append_message(conv.roles[0], input_q)
52
+ conv.append_message(conv.roles[1], None)
53
+ prompts.append(conv.get_prompt())
54
+ return prompts
55
+
56
+ def get_file_names(directory):
57
+ """返回指定目录下所有文件的名称列表（不包括子目录）。"""
58
+ file_names = [] # 创建一个空列表来存储文件名
59
+ for item in os.listdir(directory): # 遍历目录中的所有项
60
+ full_path = os.path.join(directory, item) # 获取项的完整路径
61
+ if os.path.isfile(full_path): # 检查这个路径是否是文件
62
+ file_names.append(item) # 如果是文件，则添加其名称到列表
63
+ return file_names
64
+
65
+ class Node:
66
+ def __init__(self, text, score, depth, parent=None, is_final=False):
67
+ self.text = text
68
+ self.score = score
69
+ self.depth = depth
70
+ self.parent = parent
71
+ self.children = []
72
+ self.is_final = is_final
73
+
74
+ def add_child(self, child):
75
+ self.children.append(child)
76
+
77
+ def print_paths(node, path=[]):
78
+ """
79
+ 递归函数，用于遍历树并打印从根节点到每个叶子节点的路径。
80
+ Args:
81
+ node: 当前节点。
82
+ path: 从根节点到当前节点的路径列表。
83
+ """
84
+ # 将当前节点添加到路径中
85
+ path.append(f"{node.text} (Score: {node.score}, Final: {node.is_final})")
86
+
87
+ # 如果当前节点是叶子节点，打印路径
88
+ if not node.children: # 叶子节点没有子节点
89
+ print(" -> ".join(path))
90
+ else:
91
+ # 否则，继续遍历子节点
92
+ for child in node.children:
93
+ print_paths(child, path.copy()) # 使用path.copy()以避免修改同一个列表
94
+
95
+ def sentence_level_beam_search_tree(qid, model, accelerator, processor, tokenizer, after_tokenizer, initial_text, images, sentence_end_id, max_length, max_new_tokens, num_beams, num_beam_group, token_level_beams, temperature, diversity_penalty):
96
+ """
97
+ Args:
98
+ model: HF模型，包含一个generate方法。
99
+ tokenizer: 模型的分词器。
100
+ initial_text: 开始生成的初始文本。
101
+ images: 与文本一起使用的图像。
102
+ sentence_end_id: 句子结束标记的ID。
103
+ max_length: 生成文本的最大长度。
104
+ max_new_tokens: 每次生成的新token的最大数量。
105
+ num_beams: 在每一步使用的beam数量。
106
+ temperature: 生成温度。
107
+ """
108
+ # 初始化
109
+ root = Node(initial_text, 0, 0)
110
+ active_nodes = [root] # 活跃节点列表，初始只有根节点
111
+ with torch.no_grad():
112
+ while active_nodes:
113
+ new_nodes = []
114
+
115
+ for node in active_nodes:
116
+ print(node.text)
117
+ inputs = processor(text=node.text, images=images, return_tensors="pt").to(model.device)
118
+
119
+ with torch.inference_mode():
120
+ # outputs = model.module.generate(
121
+ outputs = model.generate(
122
+ **inputs,
123
+ num_beams=token_level_beams,
124
+ eos_token_id=sentence_end_id,
125
+ num_beam_groups=num_beam_group,
126
+ diversity_penalty=diversity_penalty,
127
+ # stopping_criteria=[stopping_criteria],
128
+ # temperature=temperature,
129
+ pad_token_id=tokenizer.pad_token_id, # different models may have different pad_token_id
130
+ num_return_sequences=token_level_beams,
131
+ max_new_tokens=max_new_tokens,
132
+ output_scores=True, # must be True
133
+ return_dict_in_generate=True, # must be True, because we need the text scores
134
+ )
135
+
136
+ # 解码生成的文本
137
+ gen_sequences = outputs.sequences[:, inputs.input_ids.shape[-1]:]
138
+ gen_texts = tokenizer.batch_decode(outputs.sequences, skip_special_tokens=True)
139
+ for j, (text, score) in enumerate(zip(gen_texts, outputs.sequences_scores)):
140
+ new_score = node.score + score.item()
141
+ is_final = (tokenizer.eos_token_id in gen_sequences[j].tolist()) or (after_tokenizer.eos_token_id in gen_sequences[j].tolist() or len(tokenizer.decode(outputs.sequences[j]))>=max_length)
142
+ new_node = Node(text, new_score, node.depth + 1, node, is_final)
143
+ node.add_child(new_node)
144
+
145
+ if is_final: # 检查是否包含结束标记
146
+ pass
147
+ else:
148
+ new_nodes.append(new_node)
149
+
150
+ new_nodes.sort(key=lambda x: x.score, reverse=True)
151
+
152
+ if len(new_nodes)<num_beams:
153
+ active_nodes = new_nodes
154
+ else:
155
+ active_nodes = new_nodes[:int(num_beams/2)-1]+new_nodes[-int(num_beams/2):]
156
+
157
+ if not active_nodes:
158
+ break
159
+
160
+ return [{'id': qid, 'tree': root}]
161
+
162
+
163
+ def load_and_merge_models(model_folder_path):
164
+ # 初始化一个空的字典来保存合并的模型参数
165
+ merged_model_state_dict = {}
166
+
167
+ # 遍历文件夹中的每个模型文件
168
+ for model_file in os.listdir(model_folder_path):
169
+ if model_file.endswith('.bin'): # 只处理以 .bin 结尾的文件
170
+ file_path = os.path.join(model_folder_path, model_file)
171
+
172
+ # 使用 torch.load 加载模型
173
+ model_state_dict = torch.load(file_path, map_location='cpu')
174
+ # print(model_state_dict.keys())
175
+ # 合并模型的状态字典
176
+ for key, value in model_state_dict.items():
177
+ if key not in merged_model_state_dict:
178
+ merged_model_state_dict[key] = value
179
+ else:
180
+ # 如果需要其他的合并逻辑，可以在此实现
181
+ # 例如，将值相加、取平均等
182
+ pass
183
+ return merged_model_state_dict
184
+
185
+
186
+ def eval_model(args):
187
+ disable_torch_init()
188
+ accelerator = Accelerator()
189
+
190
+
191
+
192
+ # output_file = args.output_file
193
+ model_path = args.model_path
194
+ mapping_path=args.weight_mapping_path
195
+
196
+ with open(mapping_path, 'r', encoding='utf-8') as f1:
197
+ mapping_keys = json.load(f1)
198
+ # model = LlavaForConditionalGeneration.from_pretrained(model_path, torch_dtype=torch.float16, device_map=4)
199
+ tokenizer=AutoTokenizer.from_pretrained("llava-hf/llava-1.5-13b-hf", use_fast=False, padding_side='left')
200
+ after_tokenizer=AutoTokenizer.from_pretrained(model_path)
201
+ # tokenizer.add_tokens([DEFAULT_IMAGE_PATCH_TOKEN], special_tokens=True)
202
+ # tokenizer.add_tokens([DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN], special_tokens=True)
203
+
204
+ processor = AutoProcessor.from_pretrained("llava-hf/llava-1.5-13b-hf")
205
+
206
+
207
+
208
+ # processor.tokenizer=tokenizer
209
+ # clip_model = CLIPModel.from_pretrained(eval_model_path, torch_dtype=torch.float16)
210
+ # clip_processor = AutoProcessor.from_pretrained(eval_model_path)
211
+
212
+ with open(args.dataset_path, 'r', encoding='utf8')as fp:
213
+ my_dataset = json.load(fp) #detail+reasoning
214
+
215
+ llava_loader=get_llava_dataloader(my_dataset, 1)
216
+
217
+
218
+ # lava_loader, processor = accelerator.prepare(
219
+ # llava_loader, processor
220
+ # )
221
+
222
+ model = LlavaForConditionalGeneration.from_pretrained("llava-hf/llava-1.5-13b-hf", device_map='cpu', torch_dtype=torch.float16)
223
+ state_dicts = load_and_merge_models(model_path)
224
+ modified_weights = {}
225
+ for old_key, value in state_dicts.items():
226
+ new_key = mapping_keys.get(old_key, old_key) # 如果没有在映射表中找到旧键，则保持原键
227
+ modified_weights[new_key] = value
228
+
229
+ modified_weights['language_model.model.embed_tokens.weight'] = model.state_dict()['language_model.model.embed_tokens.weight']
230
+ modified_weights['language_model.lm_head.weight'] = model.state_dict()['language_model.lm_head.weight']
231
+
232
+ # state_dicts['model'] = modified_weights
233
+ model.load_state_dict(modified_weights, strict=True)
234
+ # torch.cuda.empty_cache()
235
+ # print(model)
236
+ model.to(accelerator.device)
237
+
238
+ llava_loader, processor= accelerator.prepare(
239
+ llava_loader, processor
240
+ )
241
+ output_dir=args.output_dir
242
+ havedone_list=get_file_names(output_dir)
243
+ # TODO: please add check here
244
+ is_ref=args.is_ref
245
+ if is_ref:
246
+ ref_json=args.ref_path
247
+ with open(ref_json, 'r') as file:
248
+ data = json.load(file)
249
+ id_list = [item['id'] for item in data]
250
+
251
+ with torch.no_grad():
252
+ for data in llava_loader:
253
+ input_questions = data['input']
254
+ input_questions = [q.replace("<image>\n", "").replace("\n<image>", "").replace("<image>", "") for q in input_questions]
255
+ image_paths=data['image']
256
+ qid=data['question_ids']
257
+ # print(qid)
258
+ images=[]
259
+
260
+ save_name=str(qid[0])+'.pkl'
261
+ # if save_name in havedone_list:
262
+ # continue
263
+
264
+ if is_ref and (str(qid[0]) not in id_list):
265
+ print('pass:', str(qid[0]))
266
+ continue
267
+
268
+ save_path = os.path.join(output_dir, save_name)
269
+
270
+ for image_path in image_paths:
271
+ images.append(Image.open(os.path.join(args.images_dir,'COCO_train2014_'+image_path)))
272
+
273
+ prompts=get_prompts(input_questions)
274
+
275
+ sentence_end_id=29889
276
+ max_length = args.max_length
277
+ token_level_beams = args.num_token_beams
278
+ temperature = args.temperature
279
+ max_new_tokens = args.max_new_tokens
280
+ diversity_penalty = args.diversity_penalty
281
+ num_beams=args.num_beams
282
+ num_beam_group=args.num_beam_group
283
+
284
+ result=gather_object(sentence_level_beam_search_tree(
285
+ qid[0],
286
+ model,
287
+ accelerator,
288
+ processor,
289
+ tokenizer,
290
+ after_tokenizer,
291
+ # clip_model,
292
+ # clip_processor,
293
+ prompts[0],
294
+ images[0],
295
+ sentence_end_id,
296
+ max_length,
297
+ max_new_tokens,
298
+ num_beams,
299
+ num_beam_group,
300
+ token_level_beams,
301
+ temperature,
302
+ diversity_penalty
303
+ ))
304
+ # print(result)
305
+ # print_paths(result[0]['tree'])
306
+ # print(qid)
307
+ # print(len(result))
308
+ if accelerator.is_main_process:
309
+ for obj in result:
310
+ # print(obj['id'])
311
+ r_save_path = os.path.join(output_dir, str(obj['id'])+'.pkl')
312
+ print(r_save_path)
313
+ save_object(obj, r_save_path)
314
+
315
+ torch.cuda.empty_cache()
316
+ accelerator.wait_for_everyone()
317
+
318
+ if __name__ == "__main__":
319
+ parser = argparse.ArgumentParser()
320
+ parser.add_argument("--model-path", type=str, default="/home/yiyangai/Projects/dongjie/StepbyStep/llava_13b_dpoed/llava_merged_dpo_13b_1epoch_1iteration")
321
+ parser.add_argument("--dataset_path", type=str, default='/home/yiyangai/Projects/dongjie/LlaVa-Instruct-150k/LLaVA-Instruct-150K/my_dataset12k.json')
322
+ parser.add_argument("--images_dir", type=str, default="../LlaVa-Instruct-150k/data/train2014")
323
+ parser.add_argument("--output_dir", type=str, default="/home/yiyangai/Projects/dongjie/StepbyStep/Save_Folder/2024-5-9-after1dpo-13b")
324
+ parser.add_argument("--temperature", type=float, default=0.3)
325
+ parser.add_argument("--diversity_penalty", type=float, default=3.0)
326
+ parser.add_argument("--num_beams", type=int, default=5)
327
+ parser.add_argument("--num_beam_group", type=int, default=5)
328
+ parser.add_argument("--num_token_beams", type=int, default=5)
329
+ parser.add_argument("--max_length", type=int, default=1024)
330
+ parser.add_argument("--max_new_tokens", type=int, default=70)
331
+ parser.add_argument("--weight_mapping_path", type=str, default='/home/yiyangai/Projects/dongjie/5de42962e78a4485afa7a05120d78d88/key_mapping_13b.json')
332
+ parser.add_argument("--is_ref", type=bool, default=False)
333
+ parser.add_argument("--ref_path", type=str, default='/home/yiyangai/Projects/dongjie/StepbyStep/Save_Folder/4-26-dataset.json')
334
+ args = parser.parse_args()
335
+
336
+ eval_model(args)
337
+
338
+
339
+
340
+