Hugging Face's logo

Spaces:
dmedhi
/
moondream
Sleeping

App Files Community
dmedhi commited on
Commit
75b17a7
•
1 Parent(s): a1ee7f1

Upload 11 files

Browse files
Files changed (11) hide show
  1. models/added_tokens.json +40 -0
  2. models/config.json +16 -0
  3. models/generation_config.json +6 -0
  4. models/merges.txt +0 -0
  5. models/model-00001-of-00002.safetensors +3 -0
  6. models/model-00002-of-00002.safetensors +3 -0
  7. models/model.safetensors.index.json +597 -0
  8. models/special_tokens_map.json +23 -0
  9. models/tokenizer.json +0 -0
  10. models/tokenizer_config.json +324 -0
  11. models/vocab.json +0 -0
models/added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
models/config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vikhyatk/moondream2",
3
+ "architectures": [
4
+ "Moondream"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "vikhyatk/moondream2--configuration_moondream.MoondreamConfig",
8
+ "AutoModelForCausalLM": "vikhyatk/moondream2--moondream.Moondream"
9
+ },
10
+ "model_type": "moondream1",
11
+ "text_config": {
12
+ "model_type": "phi"
13
+ },
14
+ "torch_dtype": "float32",
15
+ "transformers_version": "4.44.2"
16
+ }
models/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.44.2"
6
+ }
models/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
models/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4358a7608b91b0a8f151358d5402f4eb63c815278d6590bb5f377705b6aef307
3
+ size 4971042148
models/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c964066720d8e645b3d439e7c201ab5e6fe0e4647ee5e1d1621734aa2c3d82c4
3
+ size 2500964592
models/model.safetensors.index.json ADDED
@@ -0,0 +1,597 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7471932884
4
+ },
5
+ "weight_map": {
6
+ "region_model.confidence_decoder.bias": "model-00001-of-00002.safetensors",
7
+ "region_model.confidence_decoder.weight": "model-00001-of-00002.safetensors",
8
+ "region_model.position_decoder.bias": "model-00001-of-00002.safetensors",
9
+ "region_model.position_decoder.weight": "model-00001-of-00002.safetensors",
10
+ "region_model.position_encoder.bias": "model-00001-of-00002.safetensors",
11
+ "region_model.position_encoder.weight": "model-00001-of-00002.safetensors",
12
+ "region_model.position_features.weight": "model-00001-of-00002.safetensors",
13
+ "region_model.size_decoder.bias": "model-00001-of-00002.safetensors",
14
+ "region_model.size_decoder.weight": "model-00001-of-00002.safetensors",
15
+ "region_model.size_encoder.bias": "model-00001-of-00002.safetensors",
16
+ "region_model.size_encoder.weight": "model-00001-of-00002.safetensors",
17
+ "region_model.size_features.weight": "model-00001-of-00002.safetensors",
18
+ "text_model.lm_head.linear.bias": "model-00002-of-00002.safetensors",
19
+ "text_model.lm_head.linear.weight": "model-00002-of-00002.safetensors",
20
+ "text_model.lm_head.ln.bias": "model-00002-of-00002.safetensors",
21
+ "text_model.lm_head.ln.weight": "model-00002-of-00002.safetensors",
22
+ "text_model.transformer.embd.wte.weight": "model-00001-of-00002.safetensors",
23
+ "text_model.transformer.h.0.ln.bias": "model-00001-of-00002.safetensors",
24
+ "text_model.transformer.h.0.ln.weight": "model-00001-of-00002.safetensors",
25
+ "text_model.transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
26
+ "text_model.transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
27
+ "text_model.transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
28
+ "text_model.transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
29
+ "text_model.transformer.h.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
30
+ "text_model.transformer.h.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
31
+ "text_model.transformer.h.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
32
+ "text_model.transformer.h.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
33
+ "text_model.transformer.h.1.ln.bias": "model-00001-of-00002.safetensors",
34
+ "text_model.transformer.h.1.ln.weight": "model-00001-of-00002.safetensors",
35
+ "text_model.transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
36
+ "text_model.transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
37
+ "text_model.transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
38
+ "text_model.transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
39
+ "text_model.transformer.h.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
40
+ "text_model.transformer.h.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
41
+ "text_model.transformer.h.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
42
+ "text_model.transformer.h.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
43
+ "text_model.transformer.h.10.ln.bias": "model-00001-of-00002.safetensors",
44
+ "text_model.transformer.h.10.ln.weight": "model-00001-of-00002.safetensors",
45
+ "text_model.transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
46
+ "text_model.transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
47
+ "text_model.transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
48
+ "text_model.transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
49
+ "text_model.transformer.h.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
50
+ "text_model.transformer.h.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
51
+ "text_model.transformer.h.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
52
+ "text_model.transformer.h.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
53
+ "text_model.transformer.h.11.ln.bias": "model-00001-of-00002.safetensors",
54
+ "text_model.transformer.h.11.ln.weight": "model-00001-of-00002.safetensors",
55
+ "text_model.transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
56
+ "text_model.transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
57
+ "text_model.transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
58
+ "text_model.transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
59
+ "text_model.transformer.h.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
60
+ "text_model.transformer.h.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
61
+ "text_model.transformer.h.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
62
+ "text_model.transformer.h.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
63
+ "text_model.transformer.h.12.ln.bias": "model-00001-of-00002.safetensors",
64
+ "text_model.transformer.h.12.ln.weight": "model-00001-of-00002.safetensors",
65
+ "text_model.transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
66
+ "text_model.transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
67
+ "text_model.transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
68
+ "text_model.transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
69
+ "text_model.transformer.h.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
70
+ "text_model.transformer.h.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
71
+ "text_model.transformer.h.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
72
+ "text_model.transformer.h.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
73
+ "text_model.transformer.h.13.ln.bias": "model-00002-of-00002.safetensors",
74
+ "text_model.transformer.h.13.ln.weight": "model-00002-of-00002.safetensors",
75
+ "text_model.transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
76
+ "text_model.transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
77
+ "text_model.transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
78
+ "text_model.transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
79
+ "text_model.transformer.h.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
80
+ "text_model.transformer.h.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
81
+ "text_model.transformer.h.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
82
+ "text_model.transformer.h.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
83
+ "text_model.transformer.h.14.ln.bias": "model-00002-of-00002.safetensors",
84
+ "text_model.transformer.h.14.ln.weight": "model-00002-of-00002.safetensors",
85
+ "text_model.transformer.h.14.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
86
+ "text_model.transformer.h.14.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
87
+ "text_model.transformer.h.14.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
88
+ "text_model.transformer.h.14.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
89
+ "text_model.transformer.h.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
90
+ "text_model.transformer.h.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
91
+ "text_model.transformer.h.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
92
+ "text_model.transformer.h.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
93
+ "text_model.transformer.h.15.ln.bias": "model-00002-of-00002.safetensors",
94
+ "text_model.transformer.h.15.ln.weight": "model-00002-of-00002.safetensors",
95
+ "text_model.transformer.h.15.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
96
+ "text_model.transformer.h.15.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
97
+ "text_model.transformer.h.15.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
98
+ "text_model.transformer.h.15.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
99
+ "text_model.transformer.h.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
100
+ "text_model.transformer.h.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
101
+ "text_model.transformer.h.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
102
+ "text_model.transformer.h.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
103
+ "text_model.transformer.h.16.ln.bias": "model-00002-of-00002.safetensors",
104
+ "text_model.transformer.h.16.ln.weight": "model-00002-of-00002.safetensors",
105
+ "text_model.transformer.h.16.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
106
+ "text_model.transformer.h.16.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
107
+ "text_model.transformer.h.16.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
108
+ "text_model.transformer.h.16.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
109
+ "text_model.transformer.h.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
110
+ "text_model.transformer.h.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
111
+ "text_model.transformer.h.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
112
+ "text_model.transformer.h.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
113
+ "text_model.transformer.h.17.ln.bias": "model-00002-of-00002.safetensors",
114
+ "text_model.transformer.h.17.ln.weight": "model-00002-of-00002.safetensors",
115
+ "text_model.transformer.h.17.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
116
+ "text_model.transformer.h.17.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
117
+ "text_model.transformer.h.17.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
118
+ "text_model.transformer.h.17.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
119
+ "text_model.transformer.h.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
120
+ "text_model.transformer.h.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
121
+ "text_model.transformer.h.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
122
+ "text_model.transformer.h.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
123
+ "text_model.transformer.h.18.ln.bias": "model-00002-of-00002.safetensors",
124
+ "text_model.transformer.h.18.ln.weight": "model-00002-of-00002.safetensors",
125
+ "text_model.transformer.h.18.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
126
+ "text_model.transformer.h.18.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
127
+ "text_model.transformer.h.18.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
128
+ "text_model.transformer.h.18.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
129
+ "text_model.transformer.h.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
130
+ "text_model.transformer.h.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
131
+ "text_model.transformer.h.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
132
+ "text_model.transformer.h.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
133
+ "text_model.transformer.h.19.ln.bias": "model-00002-of-00002.safetensors",
134
+ "text_model.transformer.h.19.ln.weight": "model-00002-of-00002.safetensors",
135
+ "text_model.transformer.h.19.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
136
+ "text_model.transformer.h.19.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
137
+ "text_model.transformer.h.19.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
138
+ "text_model.transformer.h.19.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
139
+ "text_model.transformer.h.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
140
+ "text_model.transformer.h.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
141
+ "text_model.transformer.h.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
142
+ "text_model.transformer.h.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
143
+ "text_model.transformer.h.2.ln.bias": "model-00001-of-00002.safetensors",
144
+ "text_model.transformer.h.2.ln.weight": "model-00001-of-00002.safetensors",
145
+ "text_model.transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
146
+ "text_model.transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
147
+ "text_model.transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
148
+ "text_model.transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
149
+ "text_model.transformer.h.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
150
+ "text_model.transformer.h.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
151
+ "text_model.transformer.h.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
152
+ "text_model.transformer.h.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
153
+ "text_model.transformer.h.20.ln.bias": "model-00002-of-00002.safetensors",
154
+ "text_model.transformer.h.20.ln.weight": "model-00002-of-00002.safetensors",
155
+ "text_model.transformer.h.20.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
156
+ "text_model.transformer.h.20.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
157
+ "text_model.transformer.h.20.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
158
+ "text_model.transformer.h.20.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
159
+ "text_model.transformer.h.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
160
+ "text_model.transformer.h.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
161
+ "text_model.transformer.h.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
162
+ "text_model.transformer.h.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
163
+ "text_model.transformer.h.21.ln.bias": "model-00002-of-00002.safetensors",
164
+ "text_model.transformer.h.21.ln.weight": "model-00002-of-00002.safetensors",
165
+ "text_model.transformer.h.21.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
166
+ "text_model.transformer.h.21.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
167
+ "text_model.transformer.h.21.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
168
+ "text_model.transformer.h.21.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
169
+ "text_model.transformer.h.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
170
+ "text_model.transformer.h.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
171
+ "text_model.transformer.h.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
172
+ "text_model.transformer.h.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
173
+ "text_model.transformer.h.22.ln.bias": "model-00002-of-00002.safetensors",
174
+ "text_model.transformer.h.22.ln.weight": "model-00002-of-00002.safetensors",
175
+ "text_model.transformer.h.22.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
176
+ "text_model.transformer.h.22.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
177
+ "text_model.transformer.h.22.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
178
+ "text_model.transformer.h.22.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
179
+ "text_model.transformer.h.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
180
+ "text_model.transformer.h.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
181
+ "text_model.transformer.h.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
182
+ "text_model.transformer.h.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
183
+ "text_model.transformer.h.23.ln.bias": "model-00002-of-00002.safetensors",
184
+ "text_model.transformer.h.23.ln.weight": "model-00002-of-00002.safetensors",
185
+ "text_model.transformer.h.23.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
186
+ "text_model.transformer.h.23.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
187
+ "text_model.transformer.h.23.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
188
+ "text_model.transformer.h.23.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
189
+ "text_model.transformer.h.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
190
+ "text_model.transformer.h.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
191
+ "text_model.transformer.h.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
192
+ "text_model.transformer.h.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
193
+ "text_model.transformer.h.3.ln.bias": "model-00001-of-00002.safetensors",
194
+ "text_model.transformer.h.3.ln.weight": "model-00001-of-00002.safetensors",
195
+ "text_model.transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
196
+ "text_model.transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
197
+ "text_model.transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
198
+ "text_model.transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
199
+ "text_model.transformer.h.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
200
+ "text_model.transformer.h.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
201
+ "text_model.transformer.h.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
202
+ "text_model.transformer.h.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
203
+ "text_model.transformer.h.4.ln.bias": "model-00001-of-00002.safetensors",
204
+ "text_model.transformer.h.4.ln.weight": "model-00001-of-00002.safetensors",
205
+ "text_model.transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
206
+ "text_model.transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
207
+ "text_model.transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
208
+ "text_model.transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
209
+ "text_model.transformer.h.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
210
+ "text_model.transformer.h.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
211
+ "text_model.transformer.h.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
212
+ "text_model.transformer.h.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
213
+ "text_model.transformer.h.5.ln.bias": "model-00001-of-00002.safetensors",
214
+ "text_model.transformer.h.5.ln.weight": "model-00001-of-00002.safetensors",
215
+ "text_model.transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
216
+ "text_model.transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
217
+ "text_model.transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
218
+ "text_model.transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
219
+ "text_model.transformer.h.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
220
+ "text_model.transformer.h.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
221
+ "text_model.transformer.h.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
222
+ "text_model.transformer.h.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
223
+ "text_model.transformer.h.6.ln.bias": "model-00001-of-00002.safetensors",
224
+ "text_model.transformer.h.6.ln.weight": "model-00001-of-00002.safetensors",
225
+ "text_model.transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
226
+ "text_model.transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
227
+ "text_model.transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
228
+ "text_model.transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
229
+ "text_model.transformer.h.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
230
+ "text_model.transformer.h.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
231
+ "text_model.transformer.h.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
232
+ "text_model.transformer.h.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
233
+ "text_model.transformer.h.7.ln.bias": "model-00001-of-00002.safetensors",
234
+ "text_model.transformer.h.7.ln.weight": "model-00001-of-00002.safetensors",
235
+ "text_model.transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
236
+ "text_model.transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
237
+ "text_model.transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
238
+ "text_model.transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
239
+ "text_model.transformer.h.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
240
+ "text_model.transformer.h.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
241
+ "text_model.transformer.h.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
242
+ "text_model.transformer.h.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
243
+ "text_model.transformer.h.8.ln.bias": "model-00001-of-00002.safetensors",
244
+ "text_model.transformer.h.8.ln.weight": "model-00001-of-00002.safetensors",
245
+ "text_model.transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
246
+ "text_model.transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
247
+ "text_model.transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
248
+ "text_model.transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
249
+ "text_model.transformer.h.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
250
+ "text_model.transformer.h.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
251
+ "text_model.transformer.h.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
252
+ "text_model.transformer.h.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
253
+ "text_model.transformer.h.9.ln.bias": "model-00001-of-00002.safetensors",
254
+ "text_model.transformer.h.9.ln.weight": "model-00001-of-00002.safetensors",
255
+ "text_model.transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
256
+ "text_model.transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
257
+ "text_model.transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
258
+ "text_model.transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
259
+ "text_model.transformer.h.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
260
+ "text_model.transformer.h.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
261
+ "text_model.transformer.h.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
262
+ "text_model.transformer.h.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
263
+ "vision_encoder.encoder.model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
264
+ "vision_encoder.encoder.model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
265
+ "vision_encoder.encoder.model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
266
+ "vision_encoder.encoder.model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
267
+ "vision_encoder.encoder.model.visual.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
268
+ "vision_encoder.encoder.model.visual.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
269
+ "vision_encoder.encoder.model.visual.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
270
+ "vision_encoder.encoder.model.visual.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
271
+ "vision_encoder.encoder.model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
272
+ "vision_encoder.encoder.model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
273
+ "vision_encoder.encoder.model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
274
+ "vision_encoder.encoder.model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
275
+ "vision_encoder.encoder.model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
276
+ "vision_encoder.encoder.model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
277
+ "vision_encoder.encoder.model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
278
+ "vision_encoder.encoder.model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
279
+ "vision_encoder.encoder.model.visual.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
280
+ "vision_encoder.encoder.model.visual.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
281
+ "vision_encoder.encoder.model.visual.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
282
+ "vision_encoder.encoder.model.visual.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
283
+ "vision_encoder.encoder.model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
284
+ "vision_encoder.encoder.model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
285
+ "vision_encoder.encoder.model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
286
+ "vision_encoder.encoder.model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
287
+ "vision_encoder.encoder.model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
288
+ "vision_encoder.encoder.model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
289
+ "vision_encoder.encoder.model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
290
+ "vision_encoder.encoder.model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
291
+ "vision_encoder.encoder.model.visual.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
292
+ "vision_encoder.encoder.model.visual.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
293
+ "vision_encoder.encoder.model.visual.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
294
+ "vision_encoder.encoder.model.visual.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
295
+ "vision_encoder.encoder.model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
296
+ "vision_encoder.encoder.model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
297
+ "vision_encoder.encoder.model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
298
+ "vision_encoder.encoder.model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
299
+ "vision_encoder.encoder.model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
300
+ "vision_encoder.encoder.model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
301
+ "vision_encoder.encoder.model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
302
+ "vision_encoder.encoder.model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
303
+ "vision_encoder.encoder.model.visual.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
304
+ "vision_encoder.encoder.model.visual.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
305
+ "vision_encoder.encoder.model.visual.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
306
+ "vision_encoder.encoder.model.visual.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
307
+ "vision_encoder.encoder.model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
308
+ "vision_encoder.encoder.model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
309
+ "vision_encoder.encoder.model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
310
+ "vision_encoder.encoder.model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
311
+ "vision_encoder.encoder.model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
312
+ "vision_encoder.encoder.model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
313
+ "vision_encoder.encoder.model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
314
+ "vision_encoder.encoder.model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
315
+ "vision_encoder.encoder.model.visual.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
316
+ "vision_encoder.encoder.model.visual.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
317
+ "vision_encoder.encoder.model.visual.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
318
+ "vision_encoder.encoder.model.visual.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
319
+ "vision_encoder.encoder.model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
320
+ "vision_encoder.encoder.model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
321
+ "vision_encoder.encoder.model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
322
+ "vision_encoder.encoder.model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
323
+ "vision_encoder.encoder.model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
324
+ "vision_encoder.encoder.model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
325
+ "vision_encoder.encoder.model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
326
+ "vision_encoder.encoder.model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
327
+ "vision_encoder.encoder.model.visual.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
328
+ "vision_encoder.encoder.model.visual.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
329
+ "vision_encoder.encoder.model.visual.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
330
+ "vision_encoder.encoder.model.visual.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
331
+ "vision_encoder.encoder.model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
332
+ "vision_encoder.encoder.model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
333
+ "vision_encoder.encoder.model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
334
+ "vision_encoder.encoder.model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
335
+ "vision_encoder.encoder.model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
336
+ "vision_encoder.encoder.model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
337
+ "vision_encoder.encoder.model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
338
+ "vision_encoder.encoder.model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
339
+ "vision_encoder.encoder.model.visual.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
340
+ "vision_encoder.encoder.model.visual.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
341
+ "vision_encoder.encoder.model.visual.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
342
+ "vision_encoder.encoder.model.visual.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
343
+ "vision_encoder.encoder.model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
344
+ "vision_encoder.encoder.model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
345
+ "vision_encoder.encoder.model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
346
+ "vision_encoder.encoder.model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
347
+ "vision_encoder.encoder.model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
348
+ "vision_encoder.encoder.model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
349
+ "vision_encoder.encoder.model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
350
+ "vision_encoder.encoder.model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
351
+ "vision_encoder.encoder.model.visual.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
352
+ "vision_encoder.encoder.model.visual.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
353
+ "vision_encoder.encoder.model.visual.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
354
+ "vision_encoder.encoder.model.visual.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
355
+ "vision_encoder.encoder.model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
356
+ "vision_encoder.encoder.model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
357
+ "vision_encoder.encoder.model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
358
+ "vision_encoder.encoder.model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
359
+ "vision_encoder.encoder.model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
360
+ "vision_encoder.encoder.model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
361
+ "vision_encoder.encoder.model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
362
+ "vision_encoder.encoder.model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
363
+ "vision_encoder.encoder.model.visual.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
364
+ "vision_encoder.encoder.model.visual.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
365
+ "vision_encoder.encoder.model.visual.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
366
+ "vision_encoder.encoder.model.visual.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
367
+ "vision_encoder.encoder.model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
368
+ "vision_encoder.encoder.model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
369
+ "vision_encoder.encoder.model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
370
+ "vision_encoder.encoder.model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
371
+ "vision_encoder.encoder.model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
372
+ "vision_encoder.encoder.model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
373
+ "vision_encoder.encoder.model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
374
+ "vision_encoder.encoder.model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
375
+ "vision_encoder.encoder.model.visual.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
376
+ "vision_encoder.encoder.model.visual.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
377
+ "vision_encoder.encoder.model.visual.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
378
+ "vision_encoder.encoder.model.visual.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
379
+ "vision_encoder.encoder.model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
380
+ "vision_encoder.encoder.model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
381
+ "vision_encoder.encoder.model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
382
+ "vision_encoder.encoder.model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
383
+ "vision_encoder.encoder.model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
384
+ "vision_encoder.encoder.model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
385
+ "vision_encoder.encoder.model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
386
+ "vision_encoder.encoder.model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
387
+ "vision_encoder.encoder.model.visual.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
388
+ "vision_encoder.encoder.model.visual.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
389
+ "vision_encoder.encoder.model.visual.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
390
+ "vision_encoder.encoder.model.visual.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
391
+ "vision_encoder.encoder.model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
392
+ "vision_encoder.encoder.model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
393
+ "vision_encoder.encoder.model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
394
+ "vision_encoder.encoder.model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
395
+ "vision_encoder.encoder.model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
396
+ "vision_encoder.encoder.model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
397
+ "vision_encoder.encoder.model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
398
+ "vision_encoder.encoder.model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
399
+ "vision_encoder.encoder.model.visual.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
400
+ "vision_encoder.encoder.model.visual.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
401
+ "vision_encoder.encoder.model.visual.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
402
+ "vision_encoder.encoder.model.visual.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
403
+ "vision_encoder.encoder.model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
404
+ "vision_encoder.encoder.model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
405
+ "vision_encoder.encoder.model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
406
+ "vision_encoder.encoder.model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
407
+ "vision_encoder.encoder.model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
408
+ "vision_encoder.encoder.model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
409
+ "vision_encoder.encoder.model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
410
+ "vision_encoder.encoder.model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
411
+ "vision_encoder.encoder.model.visual.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
412
+ "vision_encoder.encoder.model.visual.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
413
+ "vision_encoder.encoder.model.visual.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
414
+ "vision_encoder.encoder.model.visual.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
415
+ "vision_encoder.encoder.model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
416
+ "vision_encoder.encoder.model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
417
+ "vision_encoder.encoder.model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
418
+ "vision_encoder.encoder.model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
419
+ "vision_encoder.encoder.model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
420
+ "vision_encoder.encoder.model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
421
+ "vision_encoder.encoder.model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
422
+ "vision_encoder.encoder.model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
423
+ "vision_encoder.encoder.model.visual.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
424
+ "vision_encoder.encoder.model.visual.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
425
+ "vision_encoder.encoder.model.visual.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
426
+ "vision_encoder.encoder.model.visual.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
427
+ "vision_encoder.encoder.model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
428
+ "vision_encoder.encoder.model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
429
+ "vision_encoder.encoder.model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
430
+ "vision_encoder.encoder.model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
431
+ "vision_encoder.encoder.model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
432
+ "vision_encoder.encoder.model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
433
+ "vision_encoder.encoder.model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
434
+ "vision_encoder.encoder.model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
435
+ "vision_encoder.encoder.model.visual.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
436
+ "vision_encoder.encoder.model.visual.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
437
+ "vision_encoder.encoder.model.visual.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
438
+ "vision_encoder.encoder.model.visual.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
439
+ "vision_encoder.encoder.model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
440
+ "vision_encoder.encoder.model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
441
+ "vision_encoder.encoder.model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
442
+ "vision_encoder.encoder.model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
443
+ "vision_encoder.encoder.model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
444
+ "vision_encoder.encoder.model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
445
+ "vision_encoder.encoder.model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
446
+ "vision_encoder.encoder.model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
447
+ "vision_encoder.encoder.model.visual.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
448
+ "vision_encoder.encoder.model.visual.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
449
+ "vision_encoder.encoder.model.visual.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
450
+ "vision_encoder.encoder.model.visual.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
451
+ "vision_encoder.encoder.model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
452
+ "vision_encoder.encoder.model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
453
+ "vision_encoder.encoder.model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
454
+ "vision_encoder.encoder.model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
455
+ "vision_encoder.encoder.model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
456
+ "vision_encoder.encoder.model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
457
+ "vision_encoder.encoder.model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
458
+ "vision_encoder.encoder.model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
459
+ "vision_encoder.encoder.model.visual.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
460
+ "vision_encoder.encoder.model.visual.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
461
+ "vision_encoder.encoder.model.visual.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
462
+ "vision_encoder.encoder.model.visual.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
463
+ "vision_encoder.encoder.model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
464
+ "vision_encoder.encoder.model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
465
+ "vision_encoder.encoder.model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
466
+ "vision_encoder.encoder.model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
467
+ "vision_encoder.encoder.model.visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
468
+ "vision_encoder.encoder.model.visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
469
+ "vision_encoder.encoder.model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
470
+ "vision_encoder.encoder.model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
471
+ "vision_encoder.encoder.model.visual.blocks.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
472
+ "vision_encoder.encoder.model.visual.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
473
+ "vision_encoder.encoder.model.visual.blocks.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
474
+ "vision_encoder.encoder.model.visual.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
475
+ "vision_encoder.encoder.model.visual.blocks.24.norm1.bias": "model-00001-of-00002.safetensors",
476
+ "vision_encoder.encoder.model.visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
477
+ "vision_encoder.encoder.model.visual.blocks.24.norm2.bias": "model-00001-of-00002.safetensors",
478
+ "vision_encoder.encoder.model.visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
479
+ "vision_encoder.encoder.model.visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
480
+ "vision_encoder.encoder.model.visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
481
+ "vision_encoder.encoder.model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
482
+ "vision_encoder.encoder.model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
483
+ "vision_encoder.encoder.model.visual.blocks.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
484
+ "vision_encoder.encoder.model.visual.blocks.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
485
+ "vision_encoder.encoder.model.visual.blocks.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
486
+ "vision_encoder.encoder.model.visual.blocks.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
487
+ "vision_encoder.encoder.model.visual.blocks.25.norm1.bias": "model-00001-of-00002.safetensors",
488
+ "vision_encoder.encoder.model.visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
489
+ "vision_encoder.encoder.model.visual.blocks.25.norm2.bias": "model-00001-of-00002.safetensors",
490
+ "vision_encoder.encoder.model.visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
491
+ "vision_encoder.encoder.model.visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
492
+ "vision_encoder.encoder.model.visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
493
+ "vision_encoder.encoder.model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
494
+ "vision_encoder.encoder.model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
495
+ "vision_encoder.encoder.model.visual.blocks.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
496
+ "vision_encoder.encoder.model.visual.blocks.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
497
+ "vision_encoder.encoder.model.visual.blocks.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
498
+ "vision_encoder.encoder.model.visual.blocks.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
499
+ "vision_encoder.encoder.model.visual.blocks.26.norm1.bias": "model-00001-of-00002.safetensors",
500
+ "vision_encoder.encoder.model.visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
501
+ "vision_encoder.encoder.model.visual.blocks.26.norm2.bias": "model-00001-of-00002.safetensors",
502
+ "vision_encoder.encoder.model.visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
503
+ "vision_encoder.encoder.model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
504
+ "vision_encoder.encoder.model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
505
+ "vision_encoder.encoder.model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
506
+ "vision_encoder.encoder.model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
507
+ "vision_encoder.encoder.model.visual.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
508
+ "vision_encoder.encoder.model.visual.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
509
+ "vision_encoder.encoder.model.visual.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
510
+ "vision_encoder.encoder.model.visual.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
511
+ "vision_encoder.encoder.model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
512
+ "vision_encoder.encoder.model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
513
+ "vision_encoder.encoder.model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
514
+ "vision_encoder.encoder.model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
515
+ "vision_encoder.encoder.model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
516
+ "vision_encoder.encoder.model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
517
+ "vision_encoder.encoder.model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
518
+ "vision_encoder.encoder.model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
519
+ "vision_encoder.encoder.model.visual.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
520
+ "vision_encoder.encoder.model.visual.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
521
+ "vision_encoder.encoder.model.visual.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
522
+ "vision_encoder.encoder.model.visual.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
523
+ "vision_encoder.encoder.model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
524
+ "vision_encoder.encoder.model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
525
+ "vision_encoder.encoder.model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
526
+ "vision_encoder.encoder.model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
527
+ "vision_encoder.encoder.model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
528
+ "vision_encoder.encoder.model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
529
+ "vision_encoder.encoder.model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
530
+ "vision_encoder.encoder.model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
531
+ "vision_encoder.encoder.model.visual.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
532
+ "vision_encoder.encoder.model.visual.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
533
+ "vision_encoder.encoder.model.visual.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
534
+ "vision_encoder.encoder.model.visual.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
535
+ "vision_encoder.encoder.model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
536
+ "vision_encoder.encoder.model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
537
+ "vision_encoder.encoder.model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
538
+ "vision_encoder.encoder.model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
539
+ "vision_encoder.encoder.model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
540
+ "vision_encoder.encoder.model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
541
+ "vision_encoder.encoder.model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
542
+ "vision_encoder.encoder.model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
543
+ "vision_encoder.encoder.model.visual.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
544
+ "vision_encoder.encoder.model.visual.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
545
+ "vision_encoder.encoder.model.visual.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
546
+ "vision_encoder.encoder.model.visual.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
547
+ "vision_encoder.encoder.model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
548
+ "vision_encoder.encoder.model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
549
+ "vision_encoder.encoder.model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
550
+ "vision_encoder.encoder.model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
551
+ "vision_encoder.encoder.model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
552
+ "vision_encoder.encoder.model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
553
+ "vision_encoder.encoder.model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
554
+ "vision_encoder.encoder.model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
555
+ "vision_encoder.encoder.model.visual.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
556
+ "vision_encoder.encoder.model.visual.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
557
+ "vision_encoder.encoder.model.visual.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
558
+ "vision_encoder.encoder.model.visual.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
559
+ "vision_encoder.encoder.model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
560
+ "vision_encoder.encoder.model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
561
+ "vision_encoder.encoder.model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
562
+ "vision_encoder.encoder.model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
563
+ "vision_encoder.encoder.model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
564
+ "vision_encoder.encoder.model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
565
+ "vision_encoder.encoder.model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
566
+ "vision_encoder.encoder.model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
567
+ "vision_encoder.encoder.model.visual.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
568
+ "vision_encoder.encoder.model.visual.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
569
+ "vision_encoder.encoder.model.visual.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
570
+ "vision_encoder.encoder.model.visual.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
571
+ "vision_encoder.encoder.model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
572
+ "vision_encoder.encoder.model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
573
+ "vision_encoder.encoder.model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
574
+ "vision_encoder.encoder.model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
575
+ "vision_encoder.encoder.model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
576
+ "vision_encoder.encoder.model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
577
+ "vision_encoder.encoder.model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
578
+ "vision_encoder.encoder.model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
579
+ "vision_encoder.encoder.model.visual.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
580
+ "vision_encoder.encoder.model.visual.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
581
+ "vision_encoder.encoder.model.visual.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
582
+ "vision_encoder.encoder.model.visual.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
583
+ "vision_encoder.encoder.model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
584
+ "vision_encoder.encoder.model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
585
+ "vision_encoder.encoder.model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
586
+ "vision_encoder.encoder.model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
587
+ "vision_encoder.encoder.model.visual.norm.bias": "model-00001-of-00002.safetensors",
588
+ "vision_encoder.encoder.model.visual.norm.weight": "model-00001-of-00002.safetensors",
589
+ "vision_encoder.encoder.model.visual.patch_embed.linear.bias": "model-00001-of-00002.safetensors",
590
+ "vision_encoder.encoder.model.visual.patch_embed.linear.weight": "model-00001-of-00002.safetensors",
591
+ "vision_encoder.encoder.model.visual.pos_embed": "model-00001-of-00002.safetensors",
592
+ "vision_encoder.projection.mlp.fc1.bias": "model-00001-of-00002.safetensors",
593
+ "vision_encoder.projection.mlp.fc1.weight": "model-00001-of-00002.safetensors",
594
+ "vision_encoder.projection.mlp.fc2.bias": "model-00001-of-00002.safetensors",
595
+ "vision_encoder.projection.mlp.fc2.weight": "model-00001-of-00002.safetensors"
596
+ }
597
+ }
models/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
models/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models/tokenizer_config.json ADDED
@@ -0,0 +1,324 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "return_token_type_ids": false,
322
+ "tokenizer_class": "CodeGenTokenizer",
323
+ "unk_token": "<|endoftext|>"
324
+ }
models/vocab.json ADDED
The diff for this file is too large to render. See raw diff