Hugging Face's logo

Shoir
/
examsv_only

PyTorch
paligemma
Model card Files
xet
 Community
Shoir commited on
Commit
fc4ab36
·
verified ·
1 Parent(s): 49a7f5e

Add model checkpoint

Browse files
Files changed (10) hide show
  1. config.json +67 -0
  2. generation_config.json +8 -0
  3. optimizer.pt +3 -0
  4. pytorch_model-00001-of-00002.bin +3 -0
  5. pytorch_model-00002-of-00002.bin +3 -0
  6. pytorch_model.bin.index.json +735 -0
  7. rng_state.pth +3 -0
  8. scheduler.pt +3 -0
  9. trainer_state.json +102 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_vocab_size": 257152,
3
+ "architectures": [
4
+ "PaliGemmaForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 2,
7
+ "eos_token_id": 1,
8
+ "hidden_size": 2048,
9
+ "image_token_index": 257152,
10
+ "model_type": "paligemma",
11
+ "num_hidden_layers": 26,
12
+ "pad_token_id": 0,
13
+ "projection_dim": 2304,
14
+ "text_config": {
15
+ "architectures": [
16
+ "Gemma2ForCausalLM"
17
+ ],
18
+ "attention_bias": false,
19
+ "attention_dropout": 0.0,
20
+ "attn_logit_softcapping": 50.0,
21
+ "cache_implementation": "hybrid",
22
+ "eos_token_id": [
23
+ 1,
24
+ 107
25
+ ],
26
+ "final_logit_softcapping": 30.0,
27
+ "head_dim": 256,
28
+ "hidden_act": "gelu_pytorch_tanh",
29
+ "hidden_activation": "gelu_pytorch_tanh",
30
+ "hidden_size": 2304,
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 9216,
33
+ "max_position_embeddings": 8192,
34
+ "model_type": "gemma2",
35
+ "num_attention_heads": 8,
36
+ "num_hidden_layers": 26,
37
+ "num_image_tokens": 1024,
38
+ "num_key_value_heads": 4,
39
+ "query_pre_attn_scalar": 256,
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_theta": 10000.0,
42
+ "sliding_window": 4096,
43
+ "torch_dtype": "bfloat16",
44
+ "use_cache": true,
45
+ "vocab_size": 257216
46
+ },
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.51.3",
49
+ "vision_config": {
50
+ "attention_dropout": 0.0,
51
+ "hidden_act": "gelu_pytorch_tanh",
52
+ "hidden_size": 1152,
53
+ "image_size": 448,
54
+ "intermediate_size": 4304,
55
+ "layer_norm_eps": 1e-06,
56
+ "model_type": "siglip_vision_model",
57
+ "num_attention_heads": 16,
58
+ "num_channels": 3,
59
+ "num_hidden_layers": 27,
60
+ "num_image_tokens": 1024,
61
+ "num_positions": 256,
62
+ "patch_size": 14,
63
+ "projection_dim": 2304,
64
+ "torch_dtype": "bfloat16",
65
+ "vision_use_head": false
66
+ }
67
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": 1,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.51.3"
8
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e27779bc75ba8a3d8b5290a1e8e8b0a2bfa940f36557bc5fccbf9d59b9b8f6b3
3
+ size 10468825359
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0c1c48855f0fc123713cee2db592911dad576caa001010032e332ad4d8deaf7
3
+ size 4995243633
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25213cc10ee25858179407eea8592eed1751fd27edd7ac2c4bd94ee83b664ad1
3
+ size 1071282343
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,735 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6066254304
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.weight": "pytorch_model-00001-of-00002.bin",
7
+ "language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "language_model.model.layers.0.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
14
+ "language_model.model.layers.0.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
15
+ "language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
20
+ "language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
24
+ "language_model.model.layers.1.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
25
+ "language_model.model.layers.1.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
26
+ "language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
27
+ "language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
31
+ "language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
35
+ "language_model.model.layers.10.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
36
+ "language_model.model.layers.10.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
37
+ "language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
42
+ "language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
46
+ "language_model.model.layers.11.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
47
+ "language_model.model.layers.11.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
48
+ "language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "language_model.model.layers.12.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
58
+ "language_model.model.layers.12.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
59
+ "language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
63
+ "language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
64
+ "language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
68
+ "language_model.model.layers.13.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "language_model.model.layers.13.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
70
+ "language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
79
+ "language_model.model.layers.14.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
80
+ "language_model.model.layers.14.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
86
+ "language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
89
+ "language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
90
+ "language_model.model.layers.15.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
91
+ "language_model.model.layers.15.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
92
+ "language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
93
+ "language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
97
+ "language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
99
+ "language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
101
+ "language_model.model.layers.16.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
102
+ "language_model.model.layers.16.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
107
+ "language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
108
+ "language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
112
+ "language_model.model.layers.17.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
113
+ "language_model.model.layers.17.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
114
+ "language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
117
+ "language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
119
+ "language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
123
+ "language_model.model.layers.18.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
124
+ "language_model.model.layers.18.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
125
+ "language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
126
+ "language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
129
+ "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
130
+ "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
131
+ "language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
132
+ "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
133
+ "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
134
+ "language_model.model.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
135
+ "language_model.model.layers.19.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
136
+ "language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
138
+ "language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
139
+ "language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
141
+ "language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
143
+ "language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
144
+ "language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
145
+ "language_model.model.layers.2.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
146
+ "language_model.model.layers.2.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
147
+ "language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
152
+ "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
153
+ "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
154
+ "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
156
+ "language_model.model.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
157
+ "language_model.model.layers.20.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
158
+ "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
159
+ "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
160
+ "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
161
+ "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
162
+ "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
163
+ "language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
165
+ "language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
166
+ "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
167
+ "language_model.model.layers.21.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
168
+ "language_model.model.layers.21.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
169
+ "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
170
+ "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
171
+ "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
172
+ "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
173
+ "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
174
+ "language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
175
+ "language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
176
+ "language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
177
+ "language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
178
+ "language_model.model.layers.22.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
179
+ "language_model.model.layers.22.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
180
+ "language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
183
+ "language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
184
+ "language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
185
+ "language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "language_model.model.layers.23.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
190
+ "language_model.model.layers.23.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
191
+ "language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
193
+ "language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
196
+ "language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
197
+ "language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
198
+ "language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
199
+ "language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
200
+ "language_model.model.layers.24.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
201
+ "language_model.model.layers.24.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
202
+ "language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
203
+ "language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
205
+ "language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
206
+ "language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
207
+ "language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
209
+ "language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
211
+ "language_model.model.layers.25.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
212
+ "language_model.model.layers.25.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
213
+ "language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
216
+ "language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
217
+ "language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
218
+ "language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
219
+ "language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
220
+ "language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
222
+ "language_model.model.layers.3.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
223
+ "language_model.model.layers.3.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
224
+ "language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
225
+ "language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
226
+ "language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
227
+ "language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
228
+ "language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
229
+ "language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
230
+ "language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
231
+ "language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
232
+ "language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
233
+ "language_model.model.layers.4.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
234
+ "language_model.model.layers.4.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
235
+ "language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
236
+ "language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
237
+ "language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
238
+ "language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
239
+ "language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
240
+ "language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
241
+ "language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
242
+ "language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
243
+ "language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
244
+ "language_model.model.layers.5.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
245
+ "language_model.model.layers.5.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
246
+ "language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
247
+ "language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
249
+ "language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
250
+ "language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
251
+ "language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
252
+ "language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
253
+ "language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
254
+ "language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
255
+ "language_model.model.layers.6.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
256
+ "language_model.model.layers.6.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
257
+ "language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
258
+ "language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
259
+ "language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
260
+ "language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
261
+ "language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
262
+ "language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
264
+ "language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
265
+ "language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
266
+ "language_model.model.layers.7.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
267
+ "language_model.model.layers.7.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
268
+ "language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
269
+ "language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
270
+ "language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
273
+ "language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
274
+ "language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
277
+ "language_model.model.layers.8.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
278
+ "language_model.model.layers.8.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
279
+ "language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
283
+ "language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
284
+ "language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
286
+ "language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
287
+ "language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
288
+ "language_model.model.layers.9.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
289
+ "language_model.model.layers.9.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
290
+ "language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
292
+ "language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
293
+ "language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "language_model.model.norm.weight": "pytorch_model-00002-of-00002.bin",
295
+ "multi_modal_projector.linear.bias": "pytorch_model-00001-of-00002.bin",
296
+ "multi_modal_projector.linear.weight": "pytorch_model-00001-of-00002.bin",
297
+ "vision_tower.vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00002.bin",
298
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
299
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
300
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
301
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
302
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
303
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
304
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
305
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
306
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
307
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
308
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
309
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
310
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
311
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
313
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
314
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
315
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
316
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
317
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
318
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
319
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
320
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
321
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
322
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
323
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
324
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
325
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
326
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
327
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
328
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
329
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
330
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
331
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
332
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
333
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
334
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
335
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
336
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
337
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
338
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
339
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
340
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
341
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
342
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
343
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
344
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
345
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
346
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
347
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
348
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
349
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
350
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
351
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
352
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
353
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
354
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
355
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
356
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
357
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
358
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
359
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
360
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
361
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
362
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
363
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
364
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
365
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
366
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
367
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
368
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
369
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
370
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
371
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
372
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
373
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
374
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
375
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
376
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
377
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
378
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
379
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
380
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
381
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
382
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
383
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
384
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
385
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
386
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
387
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
388
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
389
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
390
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
391
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
392
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
393
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
394
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
395
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
396
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
397
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
398
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
399
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
400
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
401
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
402
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
403
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
404
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
405
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
406
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
407
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
408
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
409
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
410
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
411
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
412
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
413
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
414
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
415
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
416
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
417
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
418
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
419
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
420
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
421
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
422
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
423
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
424
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
425
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
426
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
427
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
428
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
429
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
430
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
431
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
432
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
433
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
434
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
435
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
436
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
437
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
438
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
439
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
440
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
441
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
442
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
443
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
444
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
445
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
446
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
447
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
448
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
449
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
450
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
451
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
452
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
453
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
454
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
455
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
456
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
457
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
458
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
459
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
460
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
461
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
462
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
463
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
464
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
465
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
466
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
467
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
468
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
469
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
470
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
471
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
472
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
473
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
474
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
475
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
476
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
477
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
478
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
479
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
480
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
481
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
482
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
483
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
484
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
485
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
486
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
487
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
488
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
489
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
490
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
491
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
492
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
493
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
494
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
495
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
496
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
497
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
498
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
499
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
500
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
501
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
502
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
503
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
504
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
505
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
506
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
507
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
508
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
509
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
510
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
511
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
512
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
513
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
514
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
515
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
516
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
517
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
518
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
519
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
520
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
521
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
522
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
523
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
524
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
525
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
526
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
527
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
528
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
529
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
530
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
531
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
532
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
533
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
534
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
535
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
536
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
537
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
538
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
539
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
540
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
541
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
542
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
543
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
544
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
545
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
546
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
547
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
548
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
549
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
550
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
551
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
552
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
553
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
554
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
555
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
556
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
557
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
558
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
559
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
560
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
561
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
562
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
563
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
564
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
565
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
566
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
567
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
568
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
569
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
570
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
571
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
572
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
573
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
574
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
575
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
576
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
577
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
578
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
579
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
580
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
581
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
582
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
583
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
584
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
585
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
586
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
587
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
588
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
589
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
590
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
591
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
592
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
593
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
594
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
595
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
596
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
597
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
598
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
599
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
600
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
601
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
602
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
603
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
604
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
605
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
606
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
607
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
608
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
609
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
610
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
611
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
612
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
613
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
614
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
615
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
616
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
617
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
618
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
619
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
620
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
621
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
622
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
623
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
624
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
625
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
626
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
627
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
628
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
629
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
630
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
631
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
632
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
633
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
634
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
635
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
636
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
637
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
638
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
639
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
640
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
641
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
642
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
643
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
644
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
645
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
646
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
647
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
648
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
649
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
650
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
651
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
652
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
653
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
654
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
655
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
656
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
657
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
658
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
659
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
660
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
661
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
662
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
663
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
664
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
665
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
666
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
667
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
668
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
669
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
670
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
671
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
672
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
673
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
674
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
675
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
676
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
677
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
678
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
679
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
680
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
681
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
682
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
683
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
684
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
685
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
686
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
687
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
688
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
689
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
690
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
691
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
692
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
693
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
694
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
695
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
696
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
697
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
698
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
699
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
700
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
701
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
702
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
703
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
704
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
705
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
706
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
707
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
708
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
709
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
710
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
711
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
712
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
713
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
714
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
715
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
716
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
717
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
718
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
719
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
720
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
721
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
722
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
723
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
724
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
725
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
726
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
727
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
728
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
729
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
730
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
731
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
732
+ "vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
733
+ "vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin"
734
+ }
735
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17cd930da9783ca70bad4b9cdeee6a06c0acea8f34645a333c93341f487f66a3
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd5a600fb2097e95ef6d5c3de7aa9cbf2e4726d3a446234b9e7aea5c070e4066
3
+ size 1465
trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.9964267483409905,
6
+ "eval_steps": 500,
7
+ "global_step": 1220,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9964267483409903,
14
+ "eval_loss": 0.6944473385810852,
15
+ "eval_runtime": 114.7819,
16
+ "eval_samples_per_second": 7.188,
17
+ "eval_steps_per_second": 0.906,
18
+ "step": 244
19
+ },
20
+ {
21
+ "epoch": 1.0040837161817253,
22
+ "grad_norm": 90.0,
23
+ "learning_rate": 1.7553956834532375e-05,
24
+ "loss": 13.1822,
25
+ "step": 245
26
+ },
27
+ {
28
+ "epoch": 1.9964267483409903,
29
+ "eval_loss": 0.688672661781311,
30
+ "eval_runtime": 83.9218,
31
+ "eval_samples_per_second": 9.831,
32
+ "eval_steps_per_second": 1.239,
33
+ "step": 488
34
+ },
35
+ {
36
+ "epoch": 2.0081674323634506,
37
+ "grad_norm": 40.5,
38
+ "learning_rate": 1.4028776978417267e-05,
39
+ "loss": 11.0456,
40
+ "step": 490
41
+ },
42
+ {
43
+ "epoch": 2.9964267483409905,
44
+ "eval_loss": 0.7161328196525574,
45
+ "eval_runtime": 85.1515,
46
+ "eval_samples_per_second": 9.689,
47
+ "eval_steps_per_second": 1.221,
48
+ "step": 732
49
+ },
50
+ {
51
+ "epoch": 3.012251148545176,
52
+ "grad_norm": 77.0,
53
+ "learning_rate": 1.0503597122302158e-05,
54
+ "loss": 8.2545,
55
+ "step": 735
56
+ },
57
+ {
58
+ "epoch": 3.9964267483409905,
59
+ "eval_loss": 1.2752673625946045,
60
+ "eval_runtime": 83.1659,
61
+ "eval_samples_per_second": 9.92,
62
+ "eval_steps_per_second": 1.251,
63
+ "step": 976
64
+ },
65
+ {
66
+ "epoch": 4.016334864726901,
67
+ "grad_norm": 23.25,
68
+ "learning_rate": 6.978417266187051e-06,
69
+ "loss": 1.473,
70
+ "step": 980
71
+ },
72
+ {
73
+ "epoch": 4.9964267483409905,
74
+ "eval_loss": 2.4596149921417236,
75
+ "eval_runtime": 98.7355,
76
+ "eval_samples_per_second": 8.356,
77
+ "eval_steps_per_second": 1.053,
78
+ "step": 1220
79
+ }
80
+ ],
81
+ "logging_steps": 245,
82
+ "max_steps": 1464,
83
+ "num_input_tokens_seen": 0,
84
+ "num_train_epochs": 6,
85
+ "save_steps": 500,
86
+ "stateful_callbacks": {
87
+ "TrainerControl": {
88
+ "args": {
89
+ "should_epoch_stop": false,
90
+ "should_evaluate": false,
91
+ "should_log": false,
92
+ "should_save": true,
93
+ "should_training_stop": false
94
+ },
95
+ "attributes": {}
96
+ }
97
+ },
98
+ "total_flos": 1.1909651086511596e+18,
99
+ "train_batch_size": 4,
100
+ "trial_name": null,
101
+ "trial_params": null
102
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0ee27b3ee7faffd20fd08da80a2524c5dc822158d9cca80eebf8570f2332cf8
3
+ size 5777