Hugging Face's logo

LyaaaaaGames
/
distilgpt2

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Model card Files
xet
 Community
1

Adding `safetensors` variant of this model

#1
by SFconvertbot - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+105
-0
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +3 -0
  2. model-00002-of-00003.safetensors +3 -0
  3. model-00003-of-00003.safetensors +3 -0
  4. model.safetensors.index.json +96 -0
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02f878eac80c26ae1c81f6754181a38a78ea6b39be6324aa43ef2bfb482c7884
3
+ size 197448232
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a115ff23218d6fafd5ac2ef29ae77d33bba907a7bceb9b2b7dc6820c105086e
3
+ size 136502392
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c814a847c8ad20f568611ecc327b58eda693a9eaccf7515b15933b69e08dc4
3
+ size 154389632
model.safetensors.index.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 482826264.0
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "transformer.h.0.attn.bias": "model-00001-of-00003.safetensors",
8
+ "transformer.h.0.attn.c_attn.bias": "model-00001-of-00003.safetensors",
9
+ "transformer.h.0.attn.c_attn.weight": "model-00001-of-00003.safetensors",
10
+ "transformer.h.0.attn.c_proj.bias": "model-00001-of-00003.safetensors",
11
+ "transformer.h.0.attn.c_proj.weight": "model-00001-of-00003.safetensors",
12
+ "transformer.h.0.attn.masked_bias": "model-00001-of-00003.safetensors",
13
+ "transformer.h.0.ln_1.bias": "model-00001-of-00003.safetensors",
14
+ "transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
15
+ "transformer.h.0.ln_2.bias": "model-00001-of-00003.safetensors",
16
+ "transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
17
+ "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
18
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
19
+ "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
20
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
21
+ "transformer.h.1.attn.bias": "model-00001-of-00003.safetensors",
22
+ "transformer.h.1.attn.c_attn.bias": "model-00001-of-00003.safetensors",
23
+ "transformer.h.1.attn.c_attn.weight": "model-00001-of-00003.safetensors",
24
+ "transformer.h.1.attn.c_proj.bias": "model-00001-of-00003.safetensors",
25
+ "transformer.h.1.attn.c_proj.weight": "model-00001-of-00003.safetensors",
26
+ "transformer.h.1.attn.masked_bias": "model-00001-of-00003.safetensors",
27
+ "transformer.h.1.ln_1.bias": "model-00001-of-00003.safetensors",
28
+ "transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
29
+ "transformer.h.1.ln_2.bias": "model-00001-of-00003.safetensors",
30
+ "transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
31
+ "transformer.h.1.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
32
+ "transformer.h.1.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
33
+ "transformer.h.1.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
34
+ "transformer.h.1.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
35
+ "transformer.h.2.attn.bias": "model-00002-of-00003.safetensors",
36
+ "transformer.h.2.attn.c_attn.bias": "model-00002-of-00003.safetensors",
37
+ "transformer.h.2.attn.c_attn.weight": "model-00002-of-00003.safetensors",
38
+ "transformer.h.2.attn.c_proj.bias": "model-00002-of-00003.safetensors",
39
+ "transformer.h.2.attn.c_proj.weight": "model-00002-of-00003.safetensors",
40
+ "transformer.h.2.attn.masked_bias": "model-00002-of-00003.safetensors",
41
+ "transformer.h.2.ln_1.bias": "model-00002-of-00003.safetensors",
42
+ "transformer.h.2.ln_1.weight": "model-00002-of-00003.safetensors",
43
+ "transformer.h.2.ln_2.bias": "model-00002-of-00003.safetensors",
44
+ "transformer.h.2.ln_2.weight": "model-00002-of-00003.safetensors",
45
+ "transformer.h.2.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
46
+ "transformer.h.2.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
47
+ "transformer.h.2.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
48
+ "transformer.h.2.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
49
+ "transformer.h.3.attn.bias": "model-00002-of-00003.safetensors",
50
+ "transformer.h.3.attn.c_attn.bias": "model-00002-of-00003.safetensors",
51
+ "transformer.h.3.attn.c_attn.weight": "model-00002-of-00003.safetensors",
52
+ "transformer.h.3.attn.c_proj.bias": "model-00002-of-00003.safetensors",
53
+ "transformer.h.3.attn.c_proj.weight": "model-00002-of-00003.safetensors",
54
+ "transformer.h.3.attn.masked_bias": "model-00002-of-00003.safetensors",
55
+ "transformer.h.3.ln_1.bias": "model-00002-of-00003.safetensors",
56
+ "transformer.h.3.ln_1.weight": "model-00002-of-00003.safetensors",
57
+ "transformer.h.3.ln_2.bias": "model-00002-of-00003.safetensors",
58
+ "transformer.h.3.ln_2.weight": "model-00002-of-00003.safetensors",
59
+ "transformer.h.3.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
60
+ "transformer.h.3.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
61
+ "transformer.h.3.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
62
+ "transformer.h.3.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
63
+ "transformer.h.4.attn.bias": "model-00002-of-00003.safetensors",
64
+ "transformer.h.4.attn.c_attn.bias": "model-00002-of-00003.safetensors",
65
+ "transformer.h.4.attn.c_attn.weight": "model-00002-of-00003.safetensors",
66
+ "transformer.h.4.attn.c_proj.bias": "model-00002-of-00003.safetensors",
67
+ "transformer.h.4.attn.c_proj.weight": "model-00002-of-00003.safetensors",
68
+ "transformer.h.4.attn.masked_bias": "model-00002-of-00003.safetensors",
69
+ "transformer.h.4.ln_1.bias": "model-00002-of-00003.safetensors",
70
+ "transformer.h.4.ln_1.weight": "model-00002-of-00003.safetensors",
71
+ "transformer.h.4.ln_2.bias": "model-00002-of-00003.safetensors",
72
+ "transformer.h.4.ln_2.weight": "model-00002-of-00003.safetensors",
73
+ "transformer.h.4.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
74
+ "transformer.h.4.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
75
+ "transformer.h.4.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
76
+ "transformer.h.4.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
77
+ "transformer.h.5.attn.bias": "model-00002-of-00003.safetensors",
78
+ "transformer.h.5.attn.c_attn.bias": "model-00002-of-00003.safetensors",
79
+ "transformer.h.5.attn.c_attn.weight": "model-00002-of-00003.safetensors",
80
+ "transformer.h.5.attn.c_proj.bias": "model-00002-of-00003.safetensors",
81
+ "transformer.h.5.attn.c_proj.weight": "model-00002-of-00003.safetensors",
82
+ "transformer.h.5.attn.masked_bias": "model-00002-of-00003.safetensors",
83
+ "transformer.h.5.ln_1.bias": "model-00002-of-00003.safetensors",
84
+ "transformer.h.5.ln_1.weight": "model-00002-of-00003.safetensors",
85
+ "transformer.h.5.ln_2.bias": "model-00002-of-00003.safetensors",
86
+ "transformer.h.5.ln_2.weight": "model-00002-of-00003.safetensors",
87
+ "transformer.h.5.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
88
+ "transformer.h.5.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
89
+ "transformer.h.5.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
90
+ "transformer.h.5.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
91
+ "transformer.ln_f.bias": "model-00002-of-00003.safetensors",
92
+ "transformer.ln_f.weight": "model-00002-of-00003.safetensors",
93
+ "transformer.wpe.weight": "model-00001-of-00003.safetensors",
94
+ "transformer.wte.weight": "model-00001-of-00003.safetensors"
95
+ }
96
+ }