Hugging Face's logo

Xenova
/
distilgpt2

Text Generation
Transformers.js
ONNX
gpt2
Model card Files Community
Xenova HF staff commited on
Commit
0aa7002
•
1 Parent(s): e2f0553

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 +97 -0
config.json CHANGED
@@ -39,7 +39,7 @@
39
  "max_length": 50
40
  }
41
  },
42
- "transformers_version": "4.29.2",
43
  "use_cache": true,
44
  "vocab_size": 50257
45
  }
 
39
  "max_length": 50
40
  }
41
  },
42
+ "transformers_version": "4.33.0.dev0",
43
  "use_cache": true,
44
  "vocab_size": 50257
45
  }
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:e7ef148c7054e336eabf723e7e3774814188fe56aa2d438bcf27a23e8b170447
3
- size 483326403
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:247c4ef4ddfe8edf977b76e5f559c049c5f8d850e34e0ba395639afe3575ad47
3
+ size 328936111
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f21220e30679a2e582dea6144d2898432a34367d4cbf4c19f4e3f83f0da933e9
3
- size 483568163
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f33cbbbb061dfaec0f2ae9f182d39bedb587ccf84938b98f01fb19f40970c90
3
+ size 330225623
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb1498a0f8699dd6d13dbe32d7bdc1b7af43d990cde2914980638c8304f659e2
3
- size 122922457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd02dcbfccb31d289cac235f71cecad357030866fe7019f05a36b1c5692afba
3
+ size 84911479
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8de8c51bfb75ada7681e72d2b95b48a3b5fd67a1c4287b49c8f647adbf43ceae
3
- size 122560243
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3ab4d7e08ca9b8ea9a42dda13a05b7ff0f1b0c9bdc4f6eba27e7f0ceff8431
3
+ size 83502375
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c95dc59009f6e5663a0a8b1d1896fdaa48d28de4a063c117742fd4780942187d
3
- size 483330259
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9b7dd7f11facae49943e28ef08ba91d37850232962b5e945bb8bc6ede5495b
3
+ size 328939971
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5506ef1bd18f4a2ae7c77ab90f86d33bc215f9c8704e535dc62791340fb8e2f
3
- size 122565400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b329ad423b3d18ff67cb07e1ff88e8210374fd0c65b08c2f11e6c977abcb1eeb
3
+ size 83507538
quantize_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Squeeze",
8
+ "MatMul",
9
+ "Reshape",
10
+ "Slice",
11
+ "Range",
12
+ "Where",
13
+ "Constant",
14
+ "ConstantOfShape",
15
+ "Split",
16
+ "Div",
17
+ "Mul",
18
+ "Concat",
19
+ "ReduceMean",
20
+ "Shape",
21
+ "Gather",
22
+ "Sqrt",
23
+ "Tanh",
24
+ "Cast",
25
+ "Transpose",
26
+ "Sub",
27
+ "Softmax",
28
+ "Unsqueeze",
29
+ "Gemm",
30
+ "Pow",
31
+ "Add"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model_merged": {
36
+ "op_types": [
37
+ "Squeeze",
38
+ "MatMul",
39
+ "Reshape",
40
+ "Slice",
41
+ "Range",
42
+ "Where",
43
+ "Constant",
44
+ "ConstantOfShape",
45
+ "Split",
46
+ "Div",
47
+ "Mul",
48
+ "Concat",
49
+ "If",
50
+ "ReduceMean",
51
+ "Shape",
52
+ "Gather",
53
+ "Sqrt",
54
+ "Tanh",
55
+ "Cast",
56
+ "Transpose",
57
+ "Sub",
58
+ "Softmax",
59
+ "Unsqueeze",
60
+ "Gemm",
61
+ "Pow",
62
+ "Add"
63
+ ],
64
+ "weight_type": "QInt8"
65
+ },
66
+ "decoder_with_past_model": {
67
+ "op_types": [
68
+ "Squeeze",
69
+ "MatMul",
70
+ "Reshape",
71
+ "Slice",
72
+ "Range",
73
+ "Where",
74
+ "Constant",
75
+ "ConstantOfShape",
76
+ "Split",
77
+ "Div",
78
+ "Mul",
79
+ "Concat",
80
+ "ReduceMean",
81
+ "Shape",
82
+ "Gather",
83
+ "Sqrt",
84
+ "Tanh",
85
+ "Cast",
86
+ "Transpose",
87
+ "Sub",
88
+ "Softmax",
89
+ "Unsqueeze",
90
+ "Gemm",
91
+ "Pow",
92
+ "Add"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ }
96
+ }
97
+ }