Hugging Face's logo

ManopeDavid
/
gpt2-sharded-bf32-100MB-GPU

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Model card Files
xet
Community
1
SFconvertbot commited on
Commit
49de040
·
verified ·
1 Parent(s): 156d366

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 (6) hide show
  1. model-00001-of-00005.safetensors +3 -0
  2. model-00002-of-00005.safetensors +3 -0
  3. model-00003-of-00005.safetensors +3 -0
  4. model-00004-of-00005.safetensors +3 -0
  5. model-00005-of-00005.safetensors +3 -0
  6. model.safetensors.index.json +156 -0
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c19b2bbdea811c04a886f9012d933284d19bf1aeb55932d91e8a94bfa75c9e2
3
+ size 154389680
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3daa103db74902cca697d3bf29b176a317ab0fbea1af5182971841095b07d74
3
+ size 97666440
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b999cb2736e0ad6e9fc7f535e18aab4f696ac02f6faa242df1fe2b1f22e4b1f5
3
+ size 94507752
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f94e7f2c1d14c83e34637a11bdcbdb972d65553ca86f085fc9887b9e621bed01
3
+ size 94504856
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6656dfa6fed08c7a369e528aa7a3308ba8b303f091b23e1772fc04bb3f00aa84
3
+ size 56705400
model.safetensors.index.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 497759232
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00001-of-00005.safetensors",
7
+ "transformer.h.0.attn.c_attn.bias": "model-00002-of-00005.safetensors",
8
+ "transformer.h.0.attn.c_attn.weight": "model-00002-of-00005.safetensors",
9
+ "transformer.h.0.attn.c_proj.bias": "model-00002-of-00005.safetensors",
10
+ "transformer.h.0.attn.c_proj.weight": "model-00002-of-00005.safetensors",
11
+ "transformer.h.0.ln_1.bias": "model-00002-of-00005.safetensors",
12
+ "transformer.h.0.ln_1.weight": "model-00002-of-00005.safetensors",
13
+ "transformer.h.0.ln_2.bias": "model-00002-of-00005.safetensors",
14
+ "transformer.h.0.ln_2.weight": "model-00002-of-00005.safetensors",
15
+ "transformer.h.0.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
16
+ "transformer.h.0.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
17
+ "transformer.h.0.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
18
+ "transformer.h.0.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
19
+ "transformer.h.1.attn.c_attn.bias": "model-00002-of-00005.safetensors",
20
+ "transformer.h.1.attn.c_attn.weight": "model-00002-of-00005.safetensors",
21
+ "transformer.h.1.attn.c_proj.bias": "model-00002-of-00005.safetensors",
22
+ "transformer.h.1.attn.c_proj.weight": "model-00002-of-00005.safetensors",
23
+ "transformer.h.1.ln_1.bias": "model-00002-of-00005.safetensors",
24
+ "transformer.h.1.ln_1.weight": "model-00002-of-00005.safetensors",
25
+ "transformer.h.1.ln_2.bias": "model-00002-of-00005.safetensors",
26
+ "transformer.h.1.ln_2.weight": "model-00002-of-00005.safetensors",
27
+ "transformer.h.1.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
28
+ "transformer.h.1.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
29
+ "transformer.h.1.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
30
+ "transformer.h.1.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
31
+ "transformer.h.10.attn.c_attn.bias": "model-00005-of-00005.safetensors",
32
+ "transformer.h.10.attn.c_attn.weight": "model-00005-of-00005.safetensors",
33
+ "transformer.h.10.attn.c_proj.bias": "model-00005-of-00005.safetensors",
34
+ "transformer.h.10.attn.c_proj.weight": "model-00005-of-00005.safetensors",
35
+ "transformer.h.10.ln_1.bias": "model-00004-of-00005.safetensors",
36
+ "transformer.h.10.ln_1.weight": "model-00004-of-00005.safetensors",
37
+ "transformer.h.10.ln_2.bias": "model-00005-of-00005.safetensors",
38
+ "transformer.h.10.ln_2.weight": "model-00005-of-00005.safetensors",
39
+ "transformer.h.10.mlp.c_fc.bias": "model-00005-of-00005.safetensors",
40
+ "transformer.h.10.mlp.c_fc.weight": "model-00005-of-00005.safetensors",
41
+ "transformer.h.10.mlp.c_proj.bias": "model-00005-of-00005.safetensors",
42
+ "transformer.h.10.mlp.c_proj.weight": "model-00005-of-00005.safetensors",
43
+ "transformer.h.11.attn.c_attn.bias": "model-00005-of-00005.safetensors",
44
+ "transformer.h.11.attn.c_attn.weight": "model-00005-of-00005.safetensors",
45
+ "transformer.h.11.attn.c_proj.bias": "model-00005-of-00005.safetensors",
46
+ "transformer.h.11.attn.c_proj.weight": "model-00005-of-00005.safetensors",
47
+ "transformer.h.11.ln_1.bias": "model-00005-of-00005.safetensors",
48
+ "transformer.h.11.ln_1.weight": "model-00005-of-00005.safetensors",
49
+ "transformer.h.11.ln_2.bias": "model-00005-of-00005.safetensors",
50
+ "transformer.h.11.ln_2.weight": "model-00005-of-00005.safetensors",
51
+ "transformer.h.11.mlp.c_fc.bias": "model-00005-of-00005.safetensors",
52
+ "transformer.h.11.mlp.c_fc.weight": "model-00005-of-00005.safetensors",
53
+ "transformer.h.11.mlp.c_proj.bias": "model-00005-of-00005.safetensors",
54
+ "transformer.h.11.mlp.c_proj.weight": "model-00005-of-00005.safetensors",
55
+ "transformer.h.2.attn.c_attn.bias": "model-00002-of-00005.safetensors",
56
+ "transformer.h.2.attn.c_attn.weight": "model-00002-of-00005.safetensors",
57
+ "transformer.h.2.attn.c_proj.bias": "model-00002-of-00005.safetensors",
58
+ "transformer.h.2.attn.c_proj.weight": "model-00002-of-00005.safetensors",
59
+ "transformer.h.2.ln_1.bias": "model-00002-of-00005.safetensors",
60
+ "transformer.h.2.ln_1.weight": "model-00002-of-00005.safetensors",
61
+ "transformer.h.2.ln_2.bias": "model-00002-of-00005.safetensors",
62
+ "transformer.h.2.ln_2.weight": "model-00002-of-00005.safetensors",
63
+ "transformer.h.2.mlp.c_fc.bias": "model-00002-of-00005.safetensors",
64
+ "transformer.h.2.mlp.c_fc.weight": "model-00002-of-00005.safetensors",
65
+ "transformer.h.2.mlp.c_proj.bias": "model-00002-of-00005.safetensors",
66
+ "transformer.h.2.mlp.c_proj.weight": "model-00002-of-00005.safetensors",
67
+ "transformer.h.3.attn.c_attn.bias": "model-00002-of-00005.safetensors",
68
+ "transformer.h.3.attn.c_attn.weight": "model-00002-of-00005.safetensors",
69
+ "transformer.h.3.attn.c_proj.bias": "model-00002-of-00005.safetensors",
70
+ "transformer.h.3.attn.c_proj.weight": "model-00002-of-00005.safetensors",
71
+ "transformer.h.3.ln_1.bias": "model-00002-of-00005.safetensors",
72
+ "transformer.h.3.ln_1.weight": "model-00002-of-00005.safetensors",
73
+ "transformer.h.3.ln_2.bias": "model-00002-of-00005.safetensors",
74
+ "transformer.h.3.ln_2.weight": "model-00002-of-00005.safetensors",
75
+ "transformer.h.3.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
76
+ "transformer.h.3.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
77
+ "transformer.h.3.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
78
+ "transformer.h.3.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
79
+ "transformer.h.4.attn.c_attn.bias": "model-00003-of-00005.safetensors",
80
+ "transformer.h.4.attn.c_attn.weight": "model-00003-of-00005.safetensors",
81
+ "transformer.h.4.attn.c_proj.bias": "model-00003-of-00005.safetensors",
82
+ "transformer.h.4.attn.c_proj.weight": "model-00003-of-00005.safetensors",
83
+ "transformer.h.4.ln_1.bias": "model-00003-of-00005.safetensors",
84
+ "transformer.h.4.ln_1.weight": "model-00003-of-00005.safetensors",
85
+ "transformer.h.4.ln_2.bias": "model-00003-of-00005.safetensors",
86
+ "transformer.h.4.ln_2.weight": "model-00003-of-00005.safetensors",
87
+ "transformer.h.4.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
88
+ "transformer.h.4.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
89
+ "transformer.h.4.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
90
+ "transformer.h.4.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
91
+ "transformer.h.5.attn.c_attn.bias": "model-00003-of-00005.safetensors",
92
+ "transformer.h.5.attn.c_attn.weight": "model-00003-of-00005.safetensors",
93
+ "transformer.h.5.attn.c_proj.bias": "model-00003-of-00005.safetensors",
94
+ "transformer.h.5.attn.c_proj.weight": "model-00003-of-00005.safetensors",
95
+ "transformer.h.5.ln_1.bias": "model-00003-of-00005.safetensors",
96
+ "transformer.h.5.ln_1.weight": "model-00003-of-00005.safetensors",
97
+ "transformer.h.5.ln_2.bias": "model-00003-of-00005.safetensors",
98
+ "transformer.h.5.ln_2.weight": "model-00003-of-00005.safetensors",
99
+ "transformer.h.5.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
100
+ "transformer.h.5.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
101
+ "transformer.h.5.mlp.c_proj.bias": "model-00003-of-00005.safetensors",
102
+ "transformer.h.5.mlp.c_proj.weight": "model-00003-of-00005.safetensors",
103
+ "transformer.h.6.attn.c_attn.bias": "model-00003-of-00005.safetensors",
104
+ "transformer.h.6.attn.c_attn.weight": "model-00003-of-00005.safetensors",
105
+ "transformer.h.6.attn.c_proj.bias": "model-00003-of-00005.safetensors",
106
+ "transformer.h.6.attn.c_proj.weight": "model-00003-of-00005.safetensors",
107
+ "transformer.h.6.ln_1.bias": "model-00003-of-00005.safetensors",
108
+ "transformer.h.6.ln_1.weight": "model-00003-of-00005.safetensors",
109
+ "transformer.h.6.ln_2.bias": "model-00003-of-00005.safetensors",
110
+ "transformer.h.6.ln_2.weight": "model-00003-of-00005.safetensors",
111
+ "transformer.h.6.mlp.c_fc.bias": "model-00003-of-00005.safetensors",
112
+ "transformer.h.6.mlp.c_fc.weight": "model-00003-of-00005.safetensors",
113
+ "transformer.h.6.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
114
+ "transformer.h.6.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
115
+ "transformer.h.7.attn.c_attn.bias": "model-00004-of-00005.safetensors",
116
+ "transformer.h.7.attn.c_attn.weight": "model-00004-of-00005.safetensors",
117
+ "transformer.h.7.attn.c_proj.bias": "model-00004-of-00005.safetensors",
118
+ "transformer.h.7.attn.c_proj.weight": "model-00004-of-00005.safetensors",
119
+ "transformer.h.7.ln_1.bias": "model-00004-of-00005.safetensors",
120
+ "transformer.h.7.ln_1.weight": "model-00004-of-00005.safetensors",
121
+ "transformer.h.7.ln_2.bias": "model-00004-of-00005.safetensors",
122
+ "transformer.h.7.ln_2.weight": "model-00004-of-00005.safetensors",
123
+ "transformer.h.7.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
124
+ "transformer.h.7.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
125
+ "transformer.h.7.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
126
+ "transformer.h.7.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
127
+ "transformer.h.8.attn.c_attn.bias": "model-00004-of-00005.safetensors",
128
+ "transformer.h.8.attn.c_attn.weight": "model-00004-of-00005.safetensors",
129
+ "transformer.h.8.attn.c_proj.bias": "model-00004-of-00005.safetensors",
130
+ "transformer.h.8.attn.c_proj.weight": "model-00004-of-00005.safetensors",
131
+ "transformer.h.8.ln_1.bias": "model-00004-of-00005.safetensors",
132
+ "transformer.h.8.ln_1.weight": "model-00004-of-00005.safetensors",
133
+ "transformer.h.8.ln_2.bias": "model-00004-of-00005.safetensors",
134
+ "transformer.h.8.ln_2.weight": "model-00004-of-00005.safetensors",
135
+ "transformer.h.8.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
136
+ "transformer.h.8.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
137
+ "transformer.h.8.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
138
+ "transformer.h.8.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
139
+ "transformer.h.9.attn.c_attn.bias": "model-00004-of-00005.safetensors",
140
+ "transformer.h.9.attn.c_attn.weight": "model-00004-of-00005.safetensors",
141
+ "transformer.h.9.attn.c_proj.bias": "model-00004-of-00005.safetensors",
142
+ "transformer.h.9.attn.c_proj.weight": "model-00004-of-00005.safetensors",
143
+ "transformer.h.9.ln_1.bias": "model-00004-of-00005.safetensors",
144
+ "transformer.h.9.ln_1.weight": "model-00004-of-00005.safetensors",
145
+ "transformer.h.9.ln_2.bias": "model-00004-of-00005.safetensors",
146
+ "transformer.h.9.ln_2.weight": "model-00004-of-00005.safetensors",
147
+ "transformer.h.9.mlp.c_fc.bias": "model-00004-of-00005.safetensors",
148
+ "transformer.h.9.mlp.c_fc.weight": "model-00004-of-00005.safetensors",
149
+ "transformer.h.9.mlp.c_proj.bias": "model-00004-of-00005.safetensors",
150
+ "transformer.h.9.mlp.c_proj.weight": "model-00004-of-00005.safetensors",
151
+ "transformer.ln_f.bias": "model-00005-of-00005.safetensors",
152
+ "transformer.ln_f.weight": "model-00005-of-00005.safetensors",
153
+ "transformer.wpe.weight": "model-00002-of-00005.safetensors",
154
+ "transformer.wte.weight": "model-00001-of-00005.safetensors"
155
+ }
156
+ }