Hugging Face's logo

vikhyatk
/
moondream1

Text Generation
Transformers
PyTorch
Safetensors
English
moondream1
custom_code
Model card Files Community
14
vikhyatk commited on
Commit
2e5a574
•
1 Parent(s): 697ea67

Upload Moondream

Browse files
Files changed (4) hide show
  1. config.json +11 -1
  2. model-00001-of-00002.safetensors +3 -0
  3. model-00002-of-00002.safetensors +3 -0
  4. model.safetensors.index.json +591 -0
config.json CHANGED
@@ -1 +1,11 @@
1
- {}
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Moondream"
4
+ ],
5
+ "model_type": "moondream",
6
+ "phi_config": {
7
+ "model_type": "phi-msft"
8
+ },
9
+ "torch_dtype": "float32",
10
+ "transformers_version": "4.36.2"
11
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66bc35d5605984971232cb42d495a2a2120b491f28110dfde273fb1cd531ec7f
3
+ size 4996191856
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2774615feaf389f3dd3ca2d92a7eeea3b86e54eb3f19d61635e2d76f1139470f
3
+ size 2568090504
model.safetensors.index.json ADDED
@@ -0,0 +1,591 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7564205504
4
+ },
5
+ "weight_map": {
6
+ "text_model.model.lm_head.linear.bias": "model-00002-of-00002.safetensors",
7
+ "text_model.model.lm_head.linear.weight": "model-00002-of-00002.safetensors",
8
+ "text_model.model.lm_head.ln.bias": "model-00002-of-00002.safetensors",
9
+ "text_model.model.lm_head.ln.weight": "model-00002-of-00002.safetensors",
10
+ "text_model.model.transformer.embd.wte.weight": "model-00001-of-00002.safetensors",
11
+ "text_model.model.transformer.h.0.ln.bias": "model-00001-of-00002.safetensors",
12
+ "text_model.model.transformer.h.0.ln.weight": "model-00001-of-00002.safetensors",
13
+ "text_model.model.transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
14
+ "text_model.model.transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
15
+ "text_model.model.transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
16
+ "text_model.model.transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
17
+ "text_model.model.transformer.h.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
18
+ "text_model.model.transformer.h.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
19
+ "text_model.model.transformer.h.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
20
+ "text_model.model.transformer.h.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
21
+ "text_model.model.transformer.h.1.ln.bias": "model-00001-of-00002.safetensors",
22
+ "text_model.model.transformer.h.1.ln.weight": "model-00001-of-00002.safetensors",
23
+ "text_model.model.transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
24
+ "text_model.model.transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
25
+ "text_model.model.transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
26
+ "text_model.model.transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
27
+ "text_model.model.transformer.h.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
28
+ "text_model.model.transformer.h.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
29
+ "text_model.model.transformer.h.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
30
+ "text_model.model.transformer.h.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
31
+ "text_model.model.transformer.h.10.ln.bias": "model-00001-of-00002.safetensors",
32
+ "text_model.model.transformer.h.10.ln.weight": "model-00001-of-00002.safetensors",
33
+ "text_model.model.transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
34
+ "text_model.model.transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
35
+ "text_model.model.transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
36
+ "text_model.model.transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
37
+ "text_model.model.transformer.h.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
38
+ "text_model.model.transformer.h.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
39
+ "text_model.model.transformer.h.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
40
+ "text_model.model.transformer.h.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
41
+ "text_model.model.transformer.h.11.ln.bias": "model-00001-of-00002.safetensors",
42
+ "text_model.model.transformer.h.11.ln.weight": "model-00001-of-00002.safetensors",
43
+ "text_model.model.transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
44
+ "text_model.model.transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
45
+ "text_model.model.transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
46
+ "text_model.model.transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
47
+ "text_model.model.transformer.h.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
48
+ "text_model.model.transformer.h.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
49
+ "text_model.model.transformer.h.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
50
+ "text_model.model.transformer.h.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
51
+ "text_model.model.transformer.h.12.ln.bias": "model-00001-of-00002.safetensors",
52
+ "text_model.model.transformer.h.12.ln.weight": "model-00001-of-00002.safetensors",
53
+ "text_model.model.transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
54
+ "text_model.model.transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
55
+ "text_model.model.transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
56
+ "text_model.model.transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
57
+ "text_model.model.transformer.h.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
58
+ "text_model.model.transformer.h.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
59
+ "text_model.model.transformer.h.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
60
+ "text_model.model.transformer.h.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
61
+ "text_model.model.transformer.h.13.ln.bias": "model-00001-of-00002.safetensors",
62
+ "text_model.model.transformer.h.13.ln.weight": "model-00001-of-00002.safetensors",
63
+ "text_model.model.transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
64
+ "text_model.model.transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
65
+ "text_model.model.transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
66
+ "text_model.model.transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
67
+ "text_model.model.transformer.h.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
68
+ "text_model.model.transformer.h.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
69
+ "text_model.model.transformer.h.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
70
+ "text_model.model.transformer.h.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
71
+ "text_model.model.transformer.h.14.ln.bias": "model-00002-of-00002.safetensors",
72
+ "text_model.model.transformer.h.14.ln.weight": "model-00002-of-00002.safetensors",
73
+ "text_model.model.transformer.h.14.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
74
+ "text_model.model.transformer.h.14.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
75
+ "text_model.model.transformer.h.14.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
76
+ "text_model.model.transformer.h.14.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
77
+ "text_model.model.transformer.h.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
78
+ "text_model.model.transformer.h.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
79
+ "text_model.model.transformer.h.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
80
+ "text_model.model.transformer.h.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
81
+ "text_model.model.transformer.h.15.ln.bias": "model-00002-of-00002.safetensors",
82
+ "text_model.model.transformer.h.15.ln.weight": "model-00002-of-00002.safetensors",
83
+ "text_model.model.transformer.h.15.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
84
+ "text_model.model.transformer.h.15.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
85
+ "text_model.model.transformer.h.15.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
86
+ "text_model.model.transformer.h.15.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
87
+ "text_model.model.transformer.h.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
88
+ "text_model.model.transformer.h.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
89
+ "text_model.model.transformer.h.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
90
+ "text_model.model.transformer.h.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
91
+ "text_model.model.transformer.h.16.ln.bias": "model-00002-of-00002.safetensors",
92
+ "text_model.model.transformer.h.16.ln.weight": "model-00002-of-00002.safetensors",
93
+ "text_model.model.transformer.h.16.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
94
+ "text_model.model.transformer.h.16.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
95
+ "text_model.model.transformer.h.16.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
96
+ "text_model.model.transformer.h.16.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
97
+ "text_model.model.transformer.h.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
98
+ "text_model.model.transformer.h.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
99
+ "text_model.model.transformer.h.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
100
+ "text_model.model.transformer.h.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
101
+ "text_model.model.transformer.h.17.ln.bias": "model-00002-of-00002.safetensors",
102
+ "text_model.model.transformer.h.17.ln.weight": "model-00002-of-00002.safetensors",
103
+ "text_model.model.transformer.h.17.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
104
+ "text_model.model.transformer.h.17.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
105
+ "text_model.model.transformer.h.17.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
106
+ "text_model.model.transformer.h.17.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
107
+ "text_model.model.transformer.h.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
108
+ "text_model.model.transformer.h.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
109
+ "text_model.model.transformer.h.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
110
+ "text_model.model.transformer.h.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
111
+ "text_model.model.transformer.h.18.ln.bias": "model-00002-of-00002.safetensors",
112
+ "text_model.model.transformer.h.18.ln.weight": "model-00002-of-00002.safetensors",
113
+ "text_model.model.transformer.h.18.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
114
+ "text_model.model.transformer.h.18.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
115
+ "text_model.model.transformer.h.18.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
116
+ "text_model.model.transformer.h.18.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
117
+ "text_model.model.transformer.h.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
118
+ "text_model.model.transformer.h.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
119
+ "text_model.model.transformer.h.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
120
+ "text_model.model.transformer.h.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
121
+ "text_model.model.transformer.h.19.ln.bias": "model-00002-of-00002.safetensors",
122
+ "text_model.model.transformer.h.19.ln.weight": "model-00002-of-00002.safetensors",
123
+ "text_model.model.transformer.h.19.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
124
+ "text_model.model.transformer.h.19.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
125
+ "text_model.model.transformer.h.19.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
126
+ "text_model.model.transformer.h.19.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
127
+ "text_model.model.transformer.h.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
128
+ "text_model.model.transformer.h.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
129
+ "text_model.model.transformer.h.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
130
+ "text_model.model.transformer.h.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
131
+ "text_model.model.transformer.h.2.ln.bias": "model-00001-of-00002.safetensors",
132
+ "text_model.model.transformer.h.2.ln.weight": "model-00001-of-00002.safetensors",
133
+ "text_model.model.transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
134
+ "text_model.model.transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
135
+ "text_model.model.transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
136
+ "text_model.model.transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
137
+ "text_model.model.transformer.h.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
138
+ "text_model.model.transformer.h.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
139
+ "text_model.model.transformer.h.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
140
+ "text_model.model.transformer.h.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
141
+ "text_model.model.transformer.h.20.ln.bias": "model-00002-of-00002.safetensors",
142
+ "text_model.model.transformer.h.20.ln.weight": "model-00002-of-00002.safetensors",
143
+ "text_model.model.transformer.h.20.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
144
+ "text_model.model.transformer.h.20.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
145
+ "text_model.model.transformer.h.20.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
146
+ "text_model.model.transformer.h.20.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
147
+ "text_model.model.transformer.h.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
148
+ "text_model.model.transformer.h.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
149
+ "text_model.model.transformer.h.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
150
+ "text_model.model.transformer.h.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
151
+ "text_model.model.transformer.h.21.ln.bias": "model-00002-of-00002.safetensors",
152
+ "text_model.model.transformer.h.21.ln.weight": "model-00002-of-00002.safetensors",
153
+ "text_model.model.transformer.h.21.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
154
+ "text_model.model.transformer.h.21.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
155
+ "text_model.model.transformer.h.21.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
156
+ "text_model.model.transformer.h.21.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
157
+ "text_model.model.transformer.h.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
158
+ "text_model.model.transformer.h.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
159
+ "text_model.model.transformer.h.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
160
+ "text_model.model.transformer.h.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
161
+ "text_model.model.transformer.h.22.ln.bias": "model-00002-of-00002.safetensors",
162
+ "text_model.model.transformer.h.22.ln.weight": "model-00002-of-00002.safetensors",
163
+ "text_model.model.transformer.h.22.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
164
+ "text_model.model.transformer.h.22.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
165
+ "text_model.model.transformer.h.22.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
166
+ "text_model.model.transformer.h.22.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
167
+ "text_model.model.transformer.h.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
168
+ "text_model.model.transformer.h.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
169
+ "text_model.model.transformer.h.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
170
+ "text_model.model.transformer.h.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
171
+ "text_model.model.transformer.h.23.ln.bias": "model-00002-of-00002.safetensors",
172
+ "text_model.model.transformer.h.23.ln.weight": "model-00002-of-00002.safetensors",
173
+ "text_model.model.transformer.h.23.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
174
+ "text_model.model.transformer.h.23.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
175
+ "text_model.model.transformer.h.23.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
176
+ "text_model.model.transformer.h.23.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
177
+ "text_model.model.transformer.h.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
178
+ "text_model.model.transformer.h.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
179
+ "text_model.model.transformer.h.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
180
+ "text_model.model.transformer.h.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
181
+ "text_model.model.transformer.h.3.ln.bias": "model-00001-of-00002.safetensors",
182
+ "text_model.model.transformer.h.3.ln.weight": "model-00001-of-00002.safetensors",
183
+ "text_model.model.transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
184
+ "text_model.model.transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
185
+ "text_model.model.transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
186
+ "text_model.model.transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
187
+ "text_model.model.transformer.h.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
188
+ "text_model.model.transformer.h.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
189
+ "text_model.model.transformer.h.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
190
+ "text_model.model.transformer.h.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
191
+ "text_model.model.transformer.h.4.ln.bias": "model-00001-of-00002.safetensors",
192
+ "text_model.model.transformer.h.4.ln.weight": "model-00001-of-00002.safetensors",
193
+ "text_model.model.transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
194
+ "text_model.model.transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
195
+ "text_model.model.transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
196
+ "text_model.model.transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
197
+ "text_model.model.transformer.h.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
198
+ "text_model.model.transformer.h.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
199
+ "text_model.model.transformer.h.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
200
+ "text_model.model.transformer.h.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
201
+ "text_model.model.transformer.h.5.ln.bias": "model-00001-of-00002.safetensors",
202
+ "text_model.model.transformer.h.5.ln.weight": "model-00001-of-00002.safetensors",
203
+ "text_model.model.transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
204
+ "text_model.model.transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
205
+ "text_model.model.transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
206
+ "text_model.model.transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
207
+ "text_model.model.transformer.h.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
208
+ "text_model.model.transformer.h.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
209
+ "text_model.model.transformer.h.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
210
+ "text_model.model.transformer.h.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
211
+ "text_model.model.transformer.h.6.ln.bias": "model-00001-of-00002.safetensors",
212
+ "text_model.model.transformer.h.6.ln.weight": "model-00001-of-00002.safetensors",
213
+ "text_model.model.transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
214
+ "text_model.model.transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
215
+ "text_model.model.transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
216
+ "text_model.model.transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
217
+ "text_model.model.transformer.h.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
218
+ "text_model.model.transformer.h.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
219
+ "text_model.model.transformer.h.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
220
+ "text_model.model.transformer.h.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
221
+ "text_model.model.transformer.h.7.ln.bias": "model-00001-of-00002.safetensors",
222
+ "text_model.model.transformer.h.7.ln.weight": "model-00001-of-00002.safetensors",
223
+ "text_model.model.transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
224
+ "text_model.model.transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
225
+ "text_model.model.transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
226
+ "text_model.model.transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
227
+ "text_model.model.transformer.h.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
228
+ "text_model.model.transformer.h.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
229
+ "text_model.model.transformer.h.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
230
+ "text_model.model.transformer.h.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
231
+ "text_model.model.transformer.h.8.ln.bias": "model-00001-of-00002.safetensors",
232
+ "text_model.model.transformer.h.8.ln.weight": "model-00001-of-00002.safetensors",
233
+ "text_model.model.transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
234
+ "text_model.model.transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
235
+ "text_model.model.transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
236
+ "text_model.model.transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
237
+ "text_model.model.transformer.h.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
238
+ "text_model.model.transformer.h.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
239
+ "text_model.model.transformer.h.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
240
+ "text_model.model.transformer.h.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
241
+ "text_model.model.transformer.h.9.ln.bias": "model-00001-of-00002.safetensors",
242
+ "text_model.model.transformer.h.9.ln.weight": "model-00001-of-00002.safetensors",
243
+ "text_model.model.transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
244
+ "text_model.model.transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
245
+ "text_model.model.transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
246
+ "text_model.model.transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
247
+ "text_model.model.transformer.h.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
248
+ "text_model.model.transformer.h.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
249
+ "text_model.model.transformer.h.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
250
+ "text_model.model.transformer.h.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
251
+ "vision_encoder.model.encoder.model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
252
+ "vision_encoder.model.encoder.model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
253
+ "vision_encoder.model.encoder.model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
254
+ "vision_encoder.model.encoder.model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
255
+ "vision_encoder.model.encoder.model.visual.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
256
+ "vision_encoder.model.encoder.model.visual.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
257
+ "vision_encoder.model.encoder.model.visual.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
258
+ "vision_encoder.model.encoder.model.visual.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
259
+ "vision_encoder.model.encoder.model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
260
+ "vision_encoder.model.encoder.model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
261
+ "vision_encoder.model.encoder.model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
262
+ "vision_encoder.model.encoder.model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
263
+ "vision_encoder.model.encoder.model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
264
+ "vision_encoder.model.encoder.model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
265
+ "vision_encoder.model.encoder.model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
266
+ "vision_encoder.model.encoder.model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
267
+ "vision_encoder.model.encoder.model.visual.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
268
+ "vision_encoder.model.encoder.model.visual.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
269
+ "vision_encoder.model.encoder.model.visual.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
270
+ "vision_encoder.model.encoder.model.visual.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
271
+ "vision_encoder.model.encoder.model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
272
+ "vision_encoder.model.encoder.model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
273
+ "vision_encoder.model.encoder.model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
274
+ "vision_encoder.model.encoder.model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
275
+ "vision_encoder.model.encoder.model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
276
+ "vision_encoder.model.encoder.model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
277
+ "vision_encoder.model.encoder.model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
278
+ "vision_encoder.model.encoder.model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
279
+ "vision_encoder.model.encoder.model.visual.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
280
+ "vision_encoder.model.encoder.model.visual.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
281
+ "vision_encoder.model.encoder.model.visual.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
282
+ "vision_encoder.model.encoder.model.visual.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
283
+ "vision_encoder.model.encoder.model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
284
+ "vision_encoder.model.encoder.model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
285
+ "vision_encoder.model.encoder.model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
286
+ "vision_encoder.model.encoder.model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
287
+ "vision_encoder.model.encoder.model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
288
+ "vision_encoder.model.encoder.model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
289
+ "vision_encoder.model.encoder.model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
290
+ "vision_encoder.model.encoder.model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
291
+ "vision_encoder.model.encoder.model.visual.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
292
+ "vision_encoder.model.encoder.model.visual.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
293
+ "vision_encoder.model.encoder.model.visual.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
294
+ "vision_encoder.model.encoder.model.visual.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
295
+ "vision_encoder.model.encoder.model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
296
+ "vision_encoder.model.encoder.model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
297
+ "vision_encoder.model.encoder.model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
298
+ "vision_encoder.model.encoder.model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
299
+ "vision_encoder.model.encoder.model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
300
+ "vision_encoder.model.encoder.model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
301
+ "vision_encoder.model.encoder.model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
302
+ "vision_encoder.model.encoder.model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
303
+ "vision_encoder.model.encoder.model.visual.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
304
+ "vision_encoder.model.encoder.model.visual.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
305
+ "vision_encoder.model.encoder.model.visual.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
306
+ "vision_encoder.model.encoder.model.visual.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
307
+ "vision_encoder.model.encoder.model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
308
+ "vision_encoder.model.encoder.model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
309
+ "vision_encoder.model.encoder.model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
310
+ "vision_encoder.model.encoder.model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
311
+ "vision_encoder.model.encoder.model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
312
+ "vision_encoder.model.encoder.model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
313
+ "vision_encoder.model.encoder.model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
314
+ "vision_encoder.model.encoder.model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
315
+ "vision_encoder.model.encoder.model.visual.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
316
+ "vision_encoder.model.encoder.model.visual.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
317
+ "vision_encoder.model.encoder.model.visual.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
318
+ "vision_encoder.model.encoder.model.visual.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
319
+ "vision_encoder.model.encoder.model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
320
+ "vision_encoder.model.encoder.model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
321
+ "vision_encoder.model.encoder.model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
322
+ "vision_encoder.model.encoder.model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
323
+ "vision_encoder.model.encoder.model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
324
+ "vision_encoder.model.encoder.model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
325
+ "vision_encoder.model.encoder.model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
326
+ "vision_encoder.model.encoder.model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
327
+ "vision_encoder.model.encoder.model.visual.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
328
+ "vision_encoder.model.encoder.model.visual.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
329
+ "vision_encoder.model.encoder.model.visual.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
330
+ "vision_encoder.model.encoder.model.visual.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
331
+ "vision_encoder.model.encoder.model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
332
+ "vision_encoder.model.encoder.model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
333
+ "vision_encoder.model.encoder.model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
334
+ "vision_encoder.model.encoder.model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
335
+ "vision_encoder.model.encoder.model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
336
+ "vision_encoder.model.encoder.model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
337
+ "vision_encoder.model.encoder.model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
338
+ "vision_encoder.model.encoder.model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
339
+ "vision_encoder.model.encoder.model.visual.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
340
+ "vision_encoder.model.encoder.model.visual.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
341
+ "vision_encoder.model.encoder.model.visual.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
342
+ "vision_encoder.model.encoder.model.visual.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
343
+ "vision_encoder.model.encoder.model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
344
+ "vision_encoder.model.encoder.model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
345
+ "vision_encoder.model.encoder.model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
346
+ "vision_encoder.model.encoder.model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
347
+ "vision_encoder.model.encoder.model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
348
+ "vision_encoder.model.encoder.model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
349
+ "vision_encoder.model.encoder.model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
350
+ "vision_encoder.model.encoder.model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
351
+ "vision_encoder.model.encoder.model.visual.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
352
+ "vision_encoder.model.encoder.model.visual.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
353
+ "vision_encoder.model.encoder.model.visual.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
354
+ "vision_encoder.model.encoder.model.visual.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
355
+ "vision_encoder.model.encoder.model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
356
+ "vision_encoder.model.encoder.model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
357
+ "vision_encoder.model.encoder.model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
358
+ "vision_encoder.model.encoder.model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
359
+ "vision_encoder.model.encoder.model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
360
+ "vision_encoder.model.encoder.model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
361
+ "vision_encoder.model.encoder.model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
362
+ "vision_encoder.model.encoder.model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
363
+ "vision_encoder.model.encoder.model.visual.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
364
+ "vision_encoder.model.encoder.model.visual.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
365
+ "vision_encoder.model.encoder.model.visual.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
366
+ "vision_encoder.model.encoder.model.visual.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
367
+ "vision_encoder.model.encoder.model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
368
+ "vision_encoder.model.encoder.model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
369
+ "vision_encoder.model.encoder.model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
370
+ "vision_encoder.model.encoder.model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
371
+ "vision_encoder.model.encoder.model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
372
+ "vision_encoder.model.encoder.model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
373
+ "vision_encoder.model.encoder.model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
374
+ "vision_encoder.model.encoder.model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
375
+ "vision_encoder.model.encoder.model.visual.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
376
+ "vision_encoder.model.encoder.model.visual.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
377
+ "vision_encoder.model.encoder.model.visual.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
378
+ "vision_encoder.model.encoder.model.visual.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
379
+ "vision_encoder.model.encoder.model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
380
+ "vision_encoder.model.encoder.model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
381
+ "vision_encoder.model.encoder.model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
382
+ "vision_encoder.model.encoder.model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
383
+ "vision_encoder.model.encoder.model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
384
+ "vision_encoder.model.encoder.model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
385
+ "vision_encoder.model.encoder.model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
386
+ "vision_encoder.model.encoder.model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
387
+ "vision_encoder.model.encoder.model.visual.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
388
+ "vision_encoder.model.encoder.model.visual.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
389
+ "vision_encoder.model.encoder.model.visual.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
390
+ "vision_encoder.model.encoder.model.visual.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
391
+ "vision_encoder.model.encoder.model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
392
+ "vision_encoder.model.encoder.model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
393
+ "vision_encoder.model.encoder.model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
394
+ "vision_encoder.model.encoder.model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
395
+ "vision_encoder.model.encoder.model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
396
+ "vision_encoder.model.encoder.model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
397
+ "vision_encoder.model.encoder.model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
398
+ "vision_encoder.model.encoder.model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
399
+ "vision_encoder.model.encoder.model.visual.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
400
+ "vision_encoder.model.encoder.model.visual.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
401
+ "vision_encoder.model.encoder.model.visual.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
402
+ "vision_encoder.model.encoder.model.visual.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
403
+ "vision_encoder.model.encoder.model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
404
+ "vision_encoder.model.encoder.model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
405
+ "vision_encoder.model.encoder.model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
406
+ "vision_encoder.model.encoder.model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
407
+ "vision_encoder.model.encoder.model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
408
+ "vision_encoder.model.encoder.model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
409
+ "vision_encoder.model.encoder.model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
410
+ "vision_encoder.model.encoder.model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
411
+ "vision_encoder.model.encoder.model.visual.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
412
+ "vision_encoder.model.encoder.model.visual.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
413
+ "vision_encoder.model.encoder.model.visual.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
414
+ "vision_encoder.model.encoder.model.visual.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
415
+ "vision_encoder.model.encoder.model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
416
+ "vision_encoder.model.encoder.model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
417
+ "vision_encoder.model.encoder.model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
418
+ "vision_encoder.model.encoder.model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
419
+ "vision_encoder.model.encoder.model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
420
+ "vision_encoder.model.encoder.model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
421
+ "vision_encoder.model.encoder.model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
422
+ "vision_encoder.model.encoder.model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
423
+ "vision_encoder.model.encoder.model.visual.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
424
+ "vision_encoder.model.encoder.model.visual.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
425
+ "vision_encoder.model.encoder.model.visual.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
426
+ "vision_encoder.model.encoder.model.visual.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
427
+ "vision_encoder.model.encoder.model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
428
+ "vision_encoder.model.encoder.model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
429
+ "vision_encoder.model.encoder.model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
430
+ "vision_encoder.model.encoder.model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
431
+ "vision_encoder.model.encoder.model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
432
+ "vision_encoder.model.encoder.model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
433
+ "vision_encoder.model.encoder.model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
434
+ "vision_encoder.model.encoder.model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
435
+ "vision_encoder.model.encoder.model.visual.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
436
+ "vision_encoder.model.encoder.model.visual.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
437
+ "vision_encoder.model.encoder.model.visual.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
438
+ "vision_encoder.model.encoder.model.visual.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
439
+ "vision_encoder.model.encoder.model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
440
+ "vision_encoder.model.encoder.model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
441
+ "vision_encoder.model.encoder.model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
442
+ "vision_encoder.model.encoder.model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
443
+ "vision_encoder.model.encoder.model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
444
+ "vision_encoder.model.encoder.model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
445
+ "vision_encoder.model.encoder.model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
446
+ "vision_encoder.model.encoder.model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
447
+ "vision_encoder.model.encoder.model.visual.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
448
+ "vision_encoder.model.encoder.model.visual.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
449
+ "vision_encoder.model.encoder.model.visual.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
450
+ "vision_encoder.model.encoder.model.visual.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
451
+ "vision_encoder.model.encoder.model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
452
+ "vision_encoder.model.encoder.model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
453
+ "vision_encoder.model.encoder.model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
454
+ "vision_encoder.model.encoder.model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
455
+ "vision_encoder.model.encoder.model.visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
456
+ "vision_encoder.model.encoder.model.visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
457
+ "vision_encoder.model.encoder.model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
458
+ "vision_encoder.model.encoder.model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
459
+ "vision_encoder.model.encoder.model.visual.blocks.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
460
+ "vision_encoder.model.encoder.model.visual.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
461
+ "vision_encoder.model.encoder.model.visual.blocks.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
462
+ "vision_encoder.model.encoder.model.visual.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
463
+ "vision_encoder.model.encoder.model.visual.blocks.24.norm1.bias": "model-00001-of-00002.safetensors",
464
+ "vision_encoder.model.encoder.model.visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
465
+ "vision_encoder.model.encoder.model.visual.blocks.24.norm2.bias": "model-00001-of-00002.safetensors",
466
+ "vision_encoder.model.encoder.model.visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
467
+ "vision_encoder.model.encoder.model.visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
468
+ "vision_encoder.model.encoder.model.visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
469
+ "vision_encoder.model.encoder.model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
470
+ "vision_encoder.model.encoder.model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
471
+ "vision_encoder.model.encoder.model.visual.blocks.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
472
+ "vision_encoder.model.encoder.model.visual.blocks.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
473
+ "vision_encoder.model.encoder.model.visual.blocks.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
474
+ "vision_encoder.model.encoder.model.visual.blocks.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
475
+ "vision_encoder.model.encoder.model.visual.blocks.25.norm1.bias": "model-00001-of-00002.safetensors",
476
+ "vision_encoder.model.encoder.model.visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
477
+ "vision_encoder.model.encoder.model.visual.blocks.25.norm2.bias": "model-00001-of-00002.safetensors",
478
+ "vision_encoder.model.encoder.model.visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
479
+ "vision_encoder.model.encoder.model.visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
480
+ "vision_encoder.model.encoder.model.visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
481
+ "vision_encoder.model.encoder.model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
482
+ "vision_encoder.model.encoder.model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
483
+ "vision_encoder.model.encoder.model.visual.blocks.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
484
+ "vision_encoder.model.encoder.model.visual.blocks.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
485
+ "vision_encoder.model.encoder.model.visual.blocks.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
486
+ "vision_encoder.model.encoder.model.visual.blocks.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
487
+ "vision_encoder.model.encoder.model.visual.blocks.26.norm1.bias": "model-00001-of-00002.safetensors",
488
+ "vision_encoder.model.encoder.model.visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
489
+ "vision_encoder.model.encoder.model.visual.blocks.26.norm2.bias": "model-00001-of-00002.safetensors",
490
+ "vision_encoder.model.encoder.model.visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
491
+ "vision_encoder.model.encoder.model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
492
+ "vision_encoder.model.encoder.model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
493
+ "vision_encoder.model.encoder.model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
494
+ "vision_encoder.model.encoder.model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
495
+ "vision_encoder.model.encoder.model.visual.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
496
+ "vision_encoder.model.encoder.model.visual.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
497
+ "vision_encoder.model.encoder.model.visual.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
498
+ "vision_encoder.model.encoder.model.visual.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
499
+ "vision_encoder.model.encoder.model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
500
+ "vision_encoder.model.encoder.model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
501
+ "vision_encoder.model.encoder.model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
502
+ "vision_encoder.model.encoder.model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
503
+ "vision_encoder.model.encoder.model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
504
+ "vision_encoder.model.encoder.model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
505
+ "vision_encoder.model.encoder.model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
506
+ "vision_encoder.model.encoder.model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
507
+ "vision_encoder.model.encoder.model.visual.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
508
+ "vision_encoder.model.encoder.model.visual.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
509
+ "vision_encoder.model.encoder.model.visual.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
510
+ "vision_encoder.model.encoder.model.visual.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
511
+ "vision_encoder.model.encoder.model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
512
+ "vision_encoder.model.encoder.model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
513
+ "vision_encoder.model.encoder.model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
514
+ "vision_encoder.model.encoder.model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
515
+ "vision_encoder.model.encoder.model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
516
+ "vision_encoder.model.encoder.model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
517
+ "vision_encoder.model.encoder.model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
518
+ "vision_encoder.model.encoder.model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
519
+ "vision_encoder.model.encoder.model.visual.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
520
+ "vision_encoder.model.encoder.model.visual.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
521
+ "vision_encoder.model.encoder.model.visual.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
522
+ "vision_encoder.model.encoder.model.visual.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
523
+ "vision_encoder.model.encoder.model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
524
+ "vision_encoder.model.encoder.model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
525
+ "vision_encoder.model.encoder.model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
526
+ "vision_encoder.model.encoder.model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
527
+ "vision_encoder.model.encoder.model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
528
+ "vision_encoder.model.encoder.model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
529
+ "vision_encoder.model.encoder.model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
530
+ "vision_encoder.model.encoder.model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
531
+ "vision_encoder.model.encoder.model.visual.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
532
+ "vision_encoder.model.encoder.model.visual.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
533
+ "vision_encoder.model.encoder.model.visual.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
534
+ "vision_encoder.model.encoder.model.visual.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
535
+ "vision_encoder.model.encoder.model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
536
+ "vision_encoder.model.encoder.model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
537
+ "vision_encoder.model.encoder.model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
538
+ "vision_encoder.model.encoder.model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
539
+ "vision_encoder.model.encoder.model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
540
+ "vision_encoder.model.encoder.model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
541
+ "vision_encoder.model.encoder.model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
542
+ "vision_encoder.model.encoder.model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
543
+ "vision_encoder.model.encoder.model.visual.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
544
+ "vision_encoder.model.encoder.model.visual.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
545
+ "vision_encoder.model.encoder.model.visual.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
546
+ "vision_encoder.model.encoder.model.visual.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
547
+ "vision_encoder.model.encoder.model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
548
+ "vision_encoder.model.encoder.model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
549
+ "vision_encoder.model.encoder.model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
550
+ "vision_encoder.model.encoder.model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
551
+ "vision_encoder.model.encoder.model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
552
+ "vision_encoder.model.encoder.model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
553
+ "vision_encoder.model.encoder.model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
554
+ "vision_encoder.model.encoder.model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
555
+ "vision_encoder.model.encoder.model.visual.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
556
+ "vision_encoder.model.encoder.model.visual.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
557
+ "vision_encoder.model.encoder.model.visual.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
558
+ "vision_encoder.model.encoder.model.visual.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
559
+ "vision_encoder.model.encoder.model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
560
+ "vision_encoder.model.encoder.model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
561
+ "vision_encoder.model.encoder.model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
562
+ "vision_encoder.model.encoder.model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
563
+ "vision_encoder.model.encoder.model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
564
+ "vision_encoder.model.encoder.model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
565
+ "vision_encoder.model.encoder.model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
566
+ "vision_encoder.model.encoder.model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
567
+ "vision_encoder.model.encoder.model.visual.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
568
+ "vision_encoder.model.encoder.model.visual.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
569
+ "vision_encoder.model.encoder.model.visual.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
570
+ "vision_encoder.model.encoder.model.visual.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
571
+ "vision_encoder.model.encoder.model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
572
+ "vision_encoder.model.encoder.model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
573
+ "vision_encoder.model.encoder.model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
574
+ "vision_encoder.model.encoder.model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
575
+ "vision_encoder.model.encoder.model.visual.norm.bias": "model-00001-of-00002.safetensors",
576
+ "vision_encoder.model.encoder.model.visual.norm.weight": "model-00001-of-00002.safetensors",
577
+ "vision_encoder.model.encoder.model.visual.patch_embed.linear.bias": "model-00001-of-00002.safetensors",
578
+ "vision_encoder.model.encoder.model.visual.patch_embed.linear.weight": "model-00001-of-00002.safetensors",
579
+ "vision_encoder.model.encoder.model.visual.pos_embed": "model-00001-of-00002.safetensors",
580
+ "vision_encoder.model.projection.ln.bias": "model-00001-of-00002.safetensors",
581
+ "vision_encoder.model.projection.ln.weight": "model-00001-of-00002.safetensors",
582
+ "vision_encoder.model.projection.mlp1.fc1.bias": "model-00001-of-00002.safetensors",
583
+ "vision_encoder.model.projection.mlp1.fc1.weight": "model-00001-of-00002.safetensors",
584
+ "vision_encoder.model.projection.mlp1.fc2.bias": "model-00001-of-00002.safetensors",
585
+ "vision_encoder.model.projection.mlp1.fc2.weight": "model-00001-of-00002.safetensors",
586
+ "vision_encoder.model.projection.mlp2.fc1.bias": "model-00001-of-00002.safetensors",
587
+ "vision_encoder.model.projection.mlp2.fc1.weight": "model-00001-of-00002.safetensors",
588
+ "vision_encoder.model.projection.mlp2.fc2.bias": "model-00001-of-00002.safetensors",
589
+ "vision_encoder.model.projection.mlp2.fc2.weight": "model-00001-of-00002.safetensors"
590
+ }
591
+ }