Hugging Face's logo

Xenova
/
gpt-neo-125M

Text Generation
Transformers.js
ONNX
gpt_neo
Model card Files Community
Xenova HF staff commited on
Commit
cbed26c
•
1 Parent(s): 2642ff7

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +1 -1
  2. generation_config.json +1 -1
  3. onnx/decoder_model.onnx +2 -2
  4. onnx/decoder_model_merged.onnx +2 -2
  5. onnx/decoder_model_merged_quantized.onnx +2 -2
  6. onnx/decoder_model_quantized.onnx +2 -2
  7. onnx/decoder_with_past_model.onnx +2 -2
  8. onnx/decoder_with_past_model_quantized.onnx +2 -2
  9. quantize_config.json +88 -0
config.json CHANGED
@@ -47,7 +47,7 @@
47
  "summary_proj_to_labels": true,
48
  "summary_type": "cls_index",
49
  "summary_use_proj": true,
50
- "transformers_version": "4.29.2",
51
  "use_cache": true,
52
  "vocab_size": 50257,
53
  "window_size": 256
 
47
  "summary_proj_to_labels": true,
48
  "summary_type": "cls_index",
49
  "summary_use_proj": true,
50
+ "transformers_version": "4.33.0.dev0",
51
  "use_cache": true,
52
  "vocab_size": 50257,
53
  "window_size": 256
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
- "transformers_version": "4.29.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
+ "transformers_version": "4.33.0.dev0"
6
  }
onnx/decoder_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f4a8d366b57be68c4f69c93d710b360a4922f89793b25755fe897b87ccb014f
3
- size 663869637
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00871334ff4eb7926f4b07f0231858255b0fcb79402e94a4143200fd828f3dbf
3
+ size 509478592
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1f20e7a37ade821c43dc654410d91fba293eac2d0cfae22c2ffff81b8a52b4f
3
- size 664174866
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a93d4be13c01d658f7098461e96c67e896397c79fbbad2f512f2ad7ffdb65122
3
+ size 518170806
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a69449f0ac812d1fa23ef46ddad943b3b770090eb00d77215de22b08e886937
3
- size 174103215
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3934849b8b8f2c03bede375252f6d0a1f04b9e9464778ce85748011f0f1bf4b
3
+ size 143637537
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2381edc2bbc024d9c696b2e6a78e4317fad3f76a5d738f647c5c49b0476776a1
3
- size 173613657
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:769c3908bb29c78de8207d1c22c10928af1077cbcac079e61011bb3560a80c25
3
+ size 134762187
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:748f1d9481b698f02fb103ced086020882933b3a4739b353107cb286752d8cba
3
- size 663877400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85bc2f7c57461729ee6e2a3e87e25a4d24fe9543126a9fbf8b0380a76c6987ac
3
+ size 509486355
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fba5ff99a179478524373933eab362af2ac74f782ea2719727967493a50021e
3
- size 173623241
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9d92306ccac644e25de041d14d1dee037cee58609d105a44c45150a404dbe40
3
+ size 134771771
quantize_config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Squeeze",
8
+ "Softmax",
9
+ "Add",
10
+ "Reshape",
11
+ "Pow",
12
+ "Concat",
13
+ "Slice",
14
+ "Mul",
15
+ "Gather",
16
+ "Unsqueeze",
17
+ "ReduceMean",
18
+ "Sub",
19
+ "Cast",
20
+ "Tanh",
21
+ "Shape",
22
+ "Constant",
23
+ "Range",
24
+ "MatMul",
25
+ "Div",
26
+ "Sqrt",
27
+ "Where",
28
+ "Transpose"
29
+ ],
30
+ "weight_type": "QInt8"
31
+ },
32
+ "decoder_model_merged": {
33
+ "op_types": [
34
+ "Squeeze",
35
+ "Softmax",
36
+ "Add",
37
+ "Reshape",
38
+ "Pow",
39
+ "Concat",
40
+ "Slice",
41
+ "Mul",
42
+ "Gather",
43
+ "Unsqueeze",
44
+ "ReduceMean",
45
+ "Sub",
46
+ "Cast",
47
+ "Tanh",
48
+ "Shape",
49
+ "Transpose",
50
+ "Range",
51
+ "If",
52
+ "MatMul",
53
+ "Div",
54
+ "Sqrt",
55
+ "Where",
56
+ "Constant"
57
+ ],
58
+ "weight_type": "QInt8"
59
+ },
60
+ "decoder_with_past_model": {
61
+ "op_types": [
62
+ "Squeeze",
63
+ "Softmax",
64
+ "Add",
65
+ "Reshape",
66
+ "Pow",
67
+ "Concat",
68
+ "Slice",
69
+ "Mul",
70
+ "Gather",
71
+ "Unsqueeze",
72
+ "ReduceMean",
73
+ "Sub",
74
+ "Cast",
75
+ "Tanh",
76
+ "Shape",
77
+ "Constant",
78
+ "Range",
79
+ "MatMul",
80
+ "Div",
81
+ "Sqrt",
82
+ "Where",
83
+ "Transpose"
84
+ ],
85
+ "weight_type": "QInt8"
86
+ }
87
+ }
88
+ }