Hugging Face's logo

cerebras
/
Cerebras-ViT-L-336-patch14-llava13b-ShareGPT4V

Transformers
PyTorch
clip_vision_model
Inference Endpoints
Model card Files Community
1
SFconvertbot commited on
Commit
e441a36
·
verified ·
1 Parent(s): 291cefc

Adding `safetensors` variant of this model

Browse files

This is an automated PR created with https://huggingface.co/spaces/safetensors/convert

This new file is equivalent to `pytorch_model.bin` but safe in the sense that
no arbitrary code can be put into it.

These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb

The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.

If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions

Feel free to ignore this PR.

Files changed (2) hide show
  1. model-00001-of-00001.safetensors +3 -0
  2. model.safetensors.index.json +398 -0
model-00001-of-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aff4e3d74f467dedf8104294f9e7aa9f04320d87d629f0412ad5f25b267765cf
3
+ size 1214077616
model.safetensors.index.json ADDED
@@ -0,0 +1,398 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 1214029824
4
+ },
5
+ "weight_map": {
6
+ "vision_model.embeddings.class_embedding": "model-00001-of-00001.safetensors",
7
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00001.safetensors",
8
+ "vision_model.embeddings.position_embedding.weight": "model-00001-of-00001.safetensors",
9
+ "vision_model.pre_layrnorm.weight": "model-00001-of-00001.safetensors",
10
+ "vision_model.pre_layrnorm.bias": "model-00001-of-00001.safetensors",
11
+ "vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
12
+ "vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
13
+ "vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
14
+ "vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
15
+ "vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
16
+ "vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
17
+ "vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
18
+ "vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
19
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00001.safetensors",
20
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00001.safetensors",
21
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00001.safetensors",
22
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00001.safetensors",
23
+ "vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00001.safetensors",
24
+ "vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00001.safetensors",
25
+ "vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00001.safetensors",
26
+ "vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00001.safetensors",
27
+ "vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
28
+ "vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
29
+ "vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
30
+ "vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
31
+ "vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
32
+ "vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
33
+ "vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
34
+ "vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
35
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00001.safetensors",
36
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00001.safetensors",
37
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00001.safetensors",
38
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00001.safetensors",
39
+ "vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00001.safetensors",
40
+ "vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00001.safetensors",
41
+ "vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00001.safetensors",
42
+ "vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00001.safetensors",
43
+ "vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
44
+ "vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
45
+ "vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
46
+ "vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
47
+ "vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
48
+ "vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
49
+ "vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
50
+ "vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
51
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00001.safetensors",
52
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00001.safetensors",
53
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00001.safetensors",
54
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00001.safetensors",
55
+ "vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00001.safetensors",
56
+ "vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00001.safetensors",
57
+ "vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00001.safetensors",
58
+ "vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00001.safetensors",
59
+ "vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
60
+ "vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
61
+ "vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
62
+ "vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
63
+ "vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
64
+ "vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
65
+ "vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
66
+ "vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
67
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00001.safetensors",
68
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00001.safetensors",
69
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00001.safetensors",
70
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00001.safetensors",
71
+ "vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00001.safetensors",
72
+ "vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00001.safetensors",
73
+ "vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00001.safetensors",
74
+ "vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00001.safetensors",
75
+ "vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
76
+ "vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
77
+ "vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
78
+ "vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
79
+ "vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
80
+ "vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
81
+ "vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
82
+ "vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
83
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00001.safetensors",
84
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00001.safetensors",
85
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00001.safetensors",
86
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00001.safetensors",
87
+ "vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00001.safetensors",
88
+ "vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00001.safetensors",
89
+ "vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00001.safetensors",
90
+ "vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00001.safetensors",
91
+ "vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
92
+ "vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
93
+ "vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
94
+ "vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
95
+ "vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
96
+ "vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
97
+ "vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
98
+ "vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
99
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00001.safetensors",
100
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00001.safetensors",
101
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00001.safetensors",
102
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00001.safetensors",
103
+ "vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00001.safetensors",
104
+ "vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00001.safetensors",
105
+ "vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00001.safetensors",
106
+ "vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00001.safetensors",
107
+ "vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
108
+ "vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
109
+ "vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
110
+ "vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
111
+ "vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
112
+ "vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
113
+ "vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
114
+ "vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
115
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00001.safetensors",
116
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00001.safetensors",
117
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00001.safetensors",
118
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00001.safetensors",
119
+ "vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00001.safetensors",
120
+ "vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00001.safetensors",
121
+ "vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00001.safetensors",
122
+ "vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00001.safetensors",
123
+ "vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
124
+ "vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
125
+ "vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
126
+ "vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
127
+ "vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
128
+ "vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
129
+ "vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
130
+ "vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
131
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00001.safetensors",
132
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00001.safetensors",
133
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00001.safetensors",
134
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00001.safetensors",
135
+ "vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00001.safetensors",
136
+ "vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00001.safetensors",
137
+ "vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00001.safetensors",
138
+ "vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00001.safetensors",
139
+ "vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
140
+ "vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
141
+ "vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
142
+ "vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
143
+ "vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
144
+ "vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
145
+ "vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
146
+ "vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
147
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00001.safetensors",
148
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00001.safetensors",
149
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00001.safetensors",
150
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00001.safetensors",
151
+ "vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00001.safetensors",
152
+ "vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00001.safetensors",
153
+ "vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00001.safetensors",
154
+ "vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00001.safetensors",
155
+ "vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
156
+ "vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
157
+ "vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
158
+ "vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
159
+ "vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
160
+ "vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
161
+ "vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
162
+ "vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
163
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00001.safetensors",
164
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00001.safetensors",
165
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00001.safetensors",
166
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00001.safetensors",
167
+ "vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00001.safetensors",
168
+ "vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00001.safetensors",
169
+ "vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00001.safetensors",
170
+ "vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00001.safetensors",
171
+ "vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
172
+ "vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
173
+ "vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
174
+ "vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
175
+ "vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
176
+ "vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
177
+ "vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
178
+ "vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
179
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00001.safetensors",
180
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00001.safetensors",
181
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00001.safetensors",
182
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00001.safetensors",
183
+ "vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00001.safetensors",
184
+ "vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00001.safetensors",
185
+ "vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00001.safetensors",
186
+ "vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00001.safetensors",
187
+ "vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
188
+ "vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
189
+ "vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
190
+ "vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
191
+ "vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
192
+ "vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
193
+ "vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
194
+ "vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
195
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00001.safetensors",
196
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00001.safetensors",
197
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00001.safetensors",
198
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00001.safetensors",
199
+ "vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00001.safetensors",
200
+ "vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00001.safetensors",
201
+ "vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00001.safetensors",
202
+ "vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00001.safetensors",
203
+ "vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
204
+ "vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
205
+ "vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
206
+ "vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
207
+ "vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
208
+ "vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
209
+ "vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
210
+ "vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
211
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00001.safetensors",
212
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00001.safetensors",
213
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00001.safetensors",
214
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00001.safetensors",
215
+ "vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00001.safetensors",
216
+ "vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00001.safetensors",
217
+ "vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00001.safetensors",
218
+ "vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00001.safetensors",
219
+ "vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
220
+ "vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
221
+ "vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
222
+ "vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
223
+ "vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
224
+ "vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
225
+ "vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
226
+ "vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
227
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00001.safetensors",
228
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00001.safetensors",
229
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00001.safetensors",
230
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00001.safetensors",
231
+ "vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00001.safetensors",
232
+ "vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00001.safetensors",
233
+ "vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00001.safetensors",
234
+ "vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00001.safetensors",
235
+ "vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
236
+ "vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
237
+ "vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
238
+ "vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
239
+ "vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
240
+ "vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
241
+ "vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
242
+ "vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
243
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00001.safetensors",
244
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00001.safetensors",
245
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00001.safetensors",
246
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00001.safetensors",
247
+ "vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00001.safetensors",
248
+ "vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00001.safetensors",
249
+ "vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00001.safetensors",
250
+ "vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00001.safetensors",
251
+ "vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
252
+ "vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
253
+ "vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
254
+ "vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
255
+ "vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
256
+ "vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
257
+ "vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
258
+ "vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
259
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00001.safetensors",
260
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00001.safetensors",
261
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00001.safetensors",
262
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00001.safetensors",
263
+ "vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00001.safetensors",
264
+ "vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00001.safetensors",
265
+ "vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00001.safetensors",
266
+ "vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00001.safetensors",
267
+ "vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
268
+ "vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
269
+ "vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
270
+ "vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
271
+ "vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
272
+ "vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
273
+ "vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
274
+ "vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
275
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00001.safetensors",
276
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00001.safetensors",
277
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00001.safetensors",
278
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00001.safetensors",
279
+ "vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00001.safetensors",
280
+ "vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00001.safetensors",
281
+ "vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00001.safetensors",
282
+ "vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00001.safetensors",
283
+ "vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
284
+ "vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
285
+ "vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
286
+ "vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
287
+ "vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
288
+ "vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
289
+ "vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
290
+ "vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
291
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00001.safetensors",
292
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00001.safetensors",
293
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00001.safetensors",
294
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00001.safetensors",
295
+ "vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00001.safetensors",
296
+ "vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00001.safetensors",
297
+ "vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00001.safetensors",
298
+ "vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00001.safetensors",
299
+ "vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
300
+ "vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
301
+ "vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
302
+ "vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
303
+ "vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
304
+ "vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
305
+ "vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
306
+ "vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
307
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00001.safetensors",
308
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00001.safetensors",
309
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00001.safetensors",
310
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00001.safetensors",
311
+ "vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00001.safetensors",
312
+ "vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00001.safetensors",
313
+ "vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00001.safetensors",
314
+ "vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00001.safetensors",
315
+ "vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
316
+ "vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
317
+ "vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
318
+ "vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
319
+ "vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
320
+ "vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
321
+ "vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
322
+ "vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
323
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00001.safetensors",
324
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00001.safetensors",
325
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00001.safetensors",
326
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00001.safetensors",
327
+ "vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00001.safetensors",
328
+ "vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00001.safetensors",
329
+ "vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00001.safetensors",
330
+ "vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00001.safetensors",
331
+ "vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
332
+ "vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
333
+ "vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
334
+ "vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
335
+ "vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
336
+ "vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
337
+ "vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
338
+ "vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
339
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00001.safetensors",
340
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00001.safetensors",
341
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00001.safetensors",
342
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00001.safetensors",
343
+ "vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00001.safetensors",
344
+ "vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00001.safetensors",
345
+ "vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00001.safetensors",
346
+ "vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00001.safetensors",
347
+ "vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
348
+ "vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
349
+ "vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
350
+ "vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
351
+ "vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
352
+ "vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
353
+ "vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
354
+ "vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
355
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00001.safetensors",
356
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00001.safetensors",
357
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00001.safetensors",
358
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00001.safetensors",
359
+ "vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00001.safetensors",
360
+ "vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00001.safetensors",
361
+ "vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00001.safetensors",
362
+ "vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00001.safetensors",
363
+ "vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
364
+ "vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
365
+ "vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
366
+ "vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
367
+ "vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
368
+ "vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
369
+ "vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
370
+ "vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
371
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00001.safetensors",
372
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00001.safetensors",
373
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00001.safetensors",
374
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00001.safetensors",
375
+ "vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00001.safetensors",
376
+ "vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00001.safetensors",
377
+ "vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00001.safetensors",
378
+ "vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00001.safetensors",
379
+ "vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
380
+ "vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
381
+ "vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
382
+ "vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
383
+ "vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
384
+ "vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
385
+ "vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
386
+ "vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
387
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00001.safetensors",
388
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00001.safetensors",
389
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00001.safetensors",
390
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00001.safetensors",
391
+ "vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00001.safetensors",
392
+ "vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00001.safetensors",
393
+ "vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00001.safetensors",
394
+ "vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00001.safetensors",
395
+ "vision_model.post_layernorm.weight": "model-00001-of-00001.safetensors",
396
+ "vision_model.post_layernorm.bias": "model-00001-of-00001.safetensors"
397
+ }
398
+ }