SFconvertbot commited on
Commit
9e5d06c
1 Parent(s): ea08385

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.

model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69d7be24418c66d932d4d112633bbeea088cf4c399537ebb1a8dc0f1457c2122
3
+ size 209715336
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e04cc752d433da9c2399249bc2e0a524c270e031bc550027d3c8d694fb507ae
3
+ size 184663112
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c91383e6c657a2fca713cf8bf497ea547eacb24b082ebe86f85c5c203718779c
3
+ size 184650824
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc21b99f77c6f08b01f186b3fdcee5e77e1a3a559ce598fec1cc983dd7894d27
3
+ size 197250232
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc9e47f1ceaa33aaf8dfb7e858025829069e781d4256bf1dfd6277044a2dd28
3
+ size 188861640
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30a6afb89b50c90136761a58cbf07a5fa74a5b7ea39ea4581ef9d26024154a60
3
+ size 184654760
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863c1fc2df070b4f3673c1ed350470ea5d6e98c32c5ffb4b540a0fb1e0648066
3
+ size 67151072
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0490546738a7536d62ad7baa8d39da0cd1315d9bd812a003408ea2cbaa80b28a
3
+ size 209715328
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e391005c83a473004c947ea8e05b1e10a5eda3d985cb27d75ed159cc01e18dd9
3
+ size 204920
model.safetensors.index.json ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 1426849792
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "model-00009-of-00009.safetensors",
7
+ "lm_head.weight": "model-00008-of-00009.safetensors",
8
+ "transformer.h.0.attn.out_proj.weight": "model-00002-of-00009.safetensors",
9
+ "transformer.h.0.attn.qkv_proj.weight": "model-00002-of-00009.safetensors",
10
+ "transformer.h.0.ln_1.bias": "model-00002-of-00009.safetensors",
11
+ "transformer.h.0.ln_1.weight": "model-00002-of-00009.safetensors",
12
+ "transformer.h.0.mlp.fc_in.bias": "model-00002-of-00009.safetensors",
13
+ "transformer.h.0.mlp.fc_in.weight": "model-00002-of-00009.safetensors",
14
+ "transformer.h.0.mlp.fc_out.bias": "model-00002-of-00009.safetensors",
15
+ "transformer.h.0.mlp.fc_out.weight": "model-00002-of-00009.safetensors",
16
+ "transformer.h.1.attn.out_proj.weight": "model-00002-of-00009.safetensors",
17
+ "transformer.h.1.attn.qkv_proj.weight": "model-00002-of-00009.safetensors",
18
+ "transformer.h.1.ln_1.bias": "model-00002-of-00009.safetensors",
19
+ "transformer.h.1.ln_1.weight": "model-00002-of-00009.safetensors",
20
+ "transformer.h.1.mlp.fc_in.bias": "model-00002-of-00009.safetensors",
21
+ "transformer.h.1.mlp.fc_in.weight": "model-00002-of-00009.safetensors",
22
+ "transformer.h.1.mlp.fc_out.bias": "model-00002-of-00009.safetensors",
23
+ "transformer.h.1.mlp.fc_out.weight": "model-00002-of-00009.safetensors",
24
+ "transformer.h.10.attn.out_proj.weight": "model-00004-of-00009.safetensors",
25
+ "transformer.h.10.attn.qkv_proj.weight": "model-00004-of-00009.safetensors",
26
+ "transformer.h.10.ln_1.bias": "model-00004-of-00009.safetensors",
27
+ "transformer.h.10.ln_1.weight": "model-00004-of-00009.safetensors",
28
+ "transformer.h.10.mlp.fc_in.bias": "model-00004-of-00009.safetensors",
29
+ "transformer.h.10.mlp.fc_in.weight": "model-00004-of-00009.safetensors",
30
+ "transformer.h.10.mlp.fc_out.bias": "model-00004-of-00009.safetensors",
31
+ "transformer.h.10.mlp.fc_out.weight": "model-00004-of-00009.safetensors",
32
+ "transformer.h.11.attn.out_proj.weight": "model-00005-of-00009.safetensors",
33
+ "transformer.h.11.attn.qkv_proj.weight": "model-00004-of-00009.safetensors",
34
+ "transformer.h.11.ln_1.bias": "model-00004-of-00009.safetensors",
35
+ "transformer.h.11.ln_1.weight": "model-00004-of-00009.safetensors",
36
+ "transformer.h.11.mlp.fc_in.bias": "model-00005-of-00009.safetensors",
37
+ "transformer.h.11.mlp.fc_in.weight": "model-00005-of-00009.safetensors",
38
+ "transformer.h.11.mlp.fc_out.bias": "model-00005-of-00009.safetensors",
39
+ "transformer.h.11.mlp.fc_out.weight": "model-00005-of-00009.safetensors",
40
+ "transformer.h.12.attn.out_proj.weight": "model-00005-of-00009.safetensors",
41
+ "transformer.h.12.attn.qkv_proj.weight": "model-00005-of-00009.safetensors",
42
+ "transformer.h.12.ln_1.bias": "model-00005-of-00009.safetensors",
43
+ "transformer.h.12.ln_1.weight": "model-00005-of-00009.safetensors",
44
+ "transformer.h.12.mlp.fc_in.bias": "model-00005-of-00009.safetensors",
45
+ "transformer.h.12.mlp.fc_in.weight": "model-00005-of-00009.safetensors",
46
+ "transformer.h.12.mlp.fc_out.bias": "model-00005-of-00009.safetensors",
47
+ "transformer.h.12.mlp.fc_out.weight": "model-00005-of-00009.safetensors",
48
+ "transformer.h.13.attn.out_proj.weight": "model-00005-of-00009.safetensors",
49
+ "transformer.h.13.attn.qkv_proj.weight": "model-00005-of-00009.safetensors",
50
+ "transformer.h.13.ln_1.bias": "model-00005-of-00009.safetensors",
51
+ "transformer.h.13.ln_1.weight": "model-00005-of-00009.safetensors",
52
+ "transformer.h.13.mlp.fc_in.bias": "model-00005-of-00009.safetensors",
53
+ "transformer.h.13.mlp.fc_in.weight": "model-00005-of-00009.safetensors",
54
+ "transformer.h.13.mlp.fc_out.bias": "model-00005-of-00009.safetensors",
55
+ "transformer.h.13.mlp.fc_out.weight": "model-00005-of-00009.safetensors",
56
+ "transformer.h.14.attn.out_proj.weight": "model-00005-of-00009.safetensors",
57
+ "transformer.h.14.attn.qkv_proj.weight": "model-00005-of-00009.safetensors",
58
+ "transformer.h.14.ln_1.bias": "model-00005-of-00009.safetensors",
59
+ "transformer.h.14.ln_1.weight": "model-00005-of-00009.safetensors",
60
+ "transformer.h.14.mlp.fc_in.bias": "model-00005-of-00009.safetensors",
61
+ "transformer.h.14.mlp.fc_in.weight": "model-00005-of-00009.safetensors",
62
+ "transformer.h.14.mlp.fc_out.bias": "model-00005-of-00009.safetensors",
63
+ "transformer.h.14.mlp.fc_out.weight": "model-00005-of-00009.safetensors",
64
+ "transformer.h.15.attn.out_proj.weight": "model-00006-of-00009.safetensors",
65
+ "transformer.h.15.attn.qkv_proj.weight": "model-00006-of-00009.safetensors",
66
+ "transformer.h.15.ln_1.bias": "model-00005-of-00009.safetensors",
67
+ "transformer.h.15.ln_1.weight": "model-00005-of-00009.safetensors",
68
+ "transformer.h.15.mlp.fc_in.bias": "model-00006-of-00009.safetensors",
69
+ "transformer.h.15.mlp.fc_in.weight": "model-00006-of-00009.safetensors",
70
+ "transformer.h.15.mlp.fc_out.bias": "model-00006-of-00009.safetensors",
71
+ "transformer.h.15.mlp.fc_out.weight": "model-00006-of-00009.safetensors",
72
+ "transformer.h.16.attn.out_proj.weight": "model-00006-of-00009.safetensors",
73
+ "transformer.h.16.attn.qkv_proj.weight": "model-00006-of-00009.safetensors",
74
+ "transformer.h.16.ln_1.bias": "model-00006-of-00009.safetensors",
75
+ "transformer.h.16.ln_1.weight": "model-00006-of-00009.safetensors",
76
+ "transformer.h.16.mlp.fc_in.bias": "model-00006-of-00009.safetensors",
77
+ "transformer.h.16.mlp.fc_in.weight": "model-00006-of-00009.safetensors",
78
+ "transformer.h.16.mlp.fc_out.bias": "model-00006-of-00009.safetensors",
79
+ "transformer.h.16.mlp.fc_out.weight": "model-00006-of-00009.safetensors",
80
+ "transformer.h.17.attn.out_proj.weight": "model-00006-of-00009.safetensors",
81
+ "transformer.h.17.attn.qkv_proj.weight": "model-00006-of-00009.safetensors",
82
+ "transformer.h.17.ln_1.bias": "model-00006-of-00009.safetensors",
83
+ "transformer.h.17.ln_1.weight": "model-00006-of-00009.safetensors",
84
+ "transformer.h.17.mlp.fc_in.bias": "model-00006-of-00009.safetensors",
85
+ "transformer.h.17.mlp.fc_in.weight": "model-00006-of-00009.safetensors",
86
+ "transformer.h.17.mlp.fc_out.bias": "model-00006-of-00009.safetensors",
87
+ "transformer.h.17.mlp.fc_out.weight": "model-00006-of-00009.safetensors",
88
+ "transformer.h.18.attn.out_proj.weight": "model-00006-of-00009.safetensors",
89
+ "transformer.h.18.attn.qkv_proj.weight": "model-00006-of-00009.safetensors",
90
+ "transformer.h.18.ln_1.bias": "model-00006-of-00009.safetensors",
91
+ "transformer.h.18.ln_1.weight": "model-00006-of-00009.safetensors",
92
+ "transformer.h.18.mlp.fc_in.bias": "model-00006-of-00009.safetensors",
93
+ "transformer.h.18.mlp.fc_in.weight": "model-00006-of-00009.safetensors",
94
+ "transformer.h.18.mlp.fc_out.bias": "model-00007-of-00009.safetensors",
95
+ "transformer.h.18.mlp.fc_out.weight": "model-00007-of-00009.safetensors",
96
+ "transformer.h.19.attn.out_proj.weight": "model-00007-of-00009.safetensors",
97
+ "transformer.h.19.attn.qkv_proj.weight": "model-00007-of-00009.safetensors",
98
+ "transformer.h.19.ln_1.bias": "model-00007-of-00009.safetensors",
99
+ "transformer.h.19.ln_1.weight": "model-00007-of-00009.safetensors",
100
+ "transformer.h.19.mlp.fc_in.bias": "model-00007-of-00009.safetensors",
101
+ "transformer.h.19.mlp.fc_in.weight": "model-00007-of-00009.safetensors",
102
+ "transformer.h.19.mlp.fc_out.bias": "model-00007-of-00009.safetensors",
103
+ "transformer.h.19.mlp.fc_out.weight": "model-00007-of-00009.safetensors",
104
+ "transformer.h.2.attn.out_proj.weight": "model-00002-of-00009.safetensors",
105
+ "transformer.h.2.attn.qkv_proj.weight": "model-00002-of-00009.safetensors",
106
+ "transformer.h.2.ln_1.bias": "model-00002-of-00009.safetensors",
107
+ "transformer.h.2.ln_1.weight": "model-00002-of-00009.safetensors",
108
+ "transformer.h.2.mlp.fc_in.bias": "model-00002-of-00009.safetensors",
109
+ "transformer.h.2.mlp.fc_in.weight": "model-00002-of-00009.safetensors",
110
+ "transformer.h.2.mlp.fc_out.bias": "model-00002-of-00009.safetensors",
111
+ "transformer.h.2.mlp.fc_out.weight": "model-00002-of-00009.safetensors",
112
+ "transformer.h.3.attn.out_proj.weight": "model-00002-of-00009.safetensors",
113
+ "transformer.h.3.attn.qkv_proj.weight": "model-00002-of-00009.safetensors",
114
+ "transformer.h.3.ln_1.bias": "model-00002-of-00009.safetensors",
115
+ "transformer.h.3.ln_1.weight": "model-00002-of-00009.safetensors",
116
+ "transformer.h.3.mlp.fc_in.bias": "model-00002-of-00009.safetensors",
117
+ "transformer.h.3.mlp.fc_in.weight": "model-00002-of-00009.safetensors",
118
+ "transformer.h.3.mlp.fc_out.bias": "model-00003-of-00009.safetensors",
119
+ "transformer.h.3.mlp.fc_out.weight": "model-00003-of-00009.safetensors",
120
+ "transformer.h.4.attn.out_proj.weight": "model-00003-of-00009.safetensors",
121
+ "transformer.h.4.attn.qkv_proj.weight": "model-00003-of-00009.safetensors",
122
+ "transformer.h.4.ln_1.bias": "model-00003-of-00009.safetensors",
123
+ "transformer.h.4.ln_1.weight": "model-00003-of-00009.safetensors",
124
+ "transformer.h.4.mlp.fc_in.bias": "model-00003-of-00009.safetensors",
125
+ "transformer.h.4.mlp.fc_in.weight": "model-00003-of-00009.safetensors",
126
+ "transformer.h.4.mlp.fc_out.bias": "model-00003-of-00009.safetensors",
127
+ "transformer.h.4.mlp.fc_out.weight": "model-00003-of-00009.safetensors",
128
+ "transformer.h.5.attn.out_proj.weight": "model-00003-of-00009.safetensors",
129
+ "transformer.h.5.attn.qkv_proj.weight": "model-00003-of-00009.safetensors",
130
+ "transformer.h.5.ln_1.bias": "model-00003-of-00009.safetensors",
131
+ "transformer.h.5.ln_1.weight": "model-00003-of-00009.safetensors",
132
+ "transformer.h.5.mlp.fc_in.bias": "model-00003-of-00009.safetensors",
133
+ "transformer.h.5.mlp.fc_in.weight": "model-00003-of-00009.safetensors",
134
+ "transformer.h.5.mlp.fc_out.bias": "model-00003-of-00009.safetensors",
135
+ "transformer.h.5.mlp.fc_out.weight": "model-00003-of-00009.safetensors",
136
+ "transformer.h.6.attn.out_proj.weight": "model-00003-of-00009.safetensors",
137
+ "transformer.h.6.attn.qkv_proj.weight": "model-00003-of-00009.safetensors",
138
+ "transformer.h.6.ln_1.bias": "model-00003-of-00009.safetensors",
139
+ "transformer.h.6.ln_1.weight": "model-00003-of-00009.safetensors",
140
+ "transformer.h.6.mlp.fc_in.bias": "model-00003-of-00009.safetensors",
141
+ "transformer.h.6.mlp.fc_in.weight": "model-00003-of-00009.safetensors",
142
+ "transformer.h.6.mlp.fc_out.bias": "model-00003-of-00009.safetensors",
143
+ "transformer.h.6.mlp.fc_out.weight": "model-00003-of-00009.safetensors",
144
+ "transformer.h.7.attn.out_proj.weight": "model-00003-of-00009.safetensors",
145
+ "transformer.h.7.attn.qkv_proj.weight": "model-00003-of-00009.safetensors",
146
+ "transformer.h.7.ln_1.bias": "model-00003-of-00009.safetensors",
147
+ "transformer.h.7.ln_1.weight": "model-00003-of-00009.safetensors",
148
+ "transformer.h.7.mlp.fc_in.bias": "model-00004-of-00009.safetensors",
149
+ "transformer.h.7.mlp.fc_in.weight": "model-00004-of-00009.safetensors",
150
+ "transformer.h.7.mlp.fc_out.bias": "model-00004-of-00009.safetensors",
151
+ "transformer.h.7.mlp.fc_out.weight": "model-00004-of-00009.safetensors",
152
+ "transformer.h.8.attn.out_proj.weight": "model-00004-of-00009.safetensors",
153
+ "transformer.h.8.attn.qkv_proj.weight": "model-00004-of-00009.safetensors",
154
+ "transformer.h.8.ln_1.bias": "model-00004-of-00009.safetensors",
155
+ "transformer.h.8.ln_1.weight": "model-00004-of-00009.safetensors",
156
+ "transformer.h.8.mlp.fc_in.bias": "model-00004-of-00009.safetensors",
157
+ "transformer.h.8.mlp.fc_in.weight": "model-00004-of-00009.safetensors",
158
+ "transformer.h.8.mlp.fc_out.bias": "model-00004-of-00009.safetensors",
159
+ "transformer.h.8.mlp.fc_out.weight": "model-00004-of-00009.safetensors",
160
+ "transformer.h.9.attn.out_proj.weight": "model-00004-of-00009.safetensors",
161
+ "transformer.h.9.attn.qkv_proj.weight": "model-00004-of-00009.safetensors",
162
+ "transformer.h.9.ln_1.bias": "model-00004-of-00009.safetensors",
163
+ "transformer.h.9.ln_1.weight": "model-00004-of-00009.safetensors",
164
+ "transformer.h.9.mlp.fc_in.bias": "model-00004-of-00009.safetensors",
165
+ "transformer.h.9.mlp.fc_in.weight": "model-00004-of-00009.safetensors",
166
+ "transformer.h.9.mlp.fc_out.bias": "model-00004-of-00009.safetensors",
167
+ "transformer.h.9.mlp.fc_out.weight": "model-00004-of-00009.safetensors",
168
+ "transformer.ln_f.bias": "model-00007-of-00009.safetensors",
169
+ "transformer.ln_f.weight": "model-00007-of-00009.safetensors",
170
+ "transformer.wte.weight": "model-00001-of-00009.safetensors"
171
+ }
172
+ }