Hugging Face's logo

ayousanz
/
any-ONNX-models

ONNX
Model card Files Community
ayousanz commited on
Commit
033b92c
•
1 Parent(s): f977093

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. rinna/japanese-gpt2-xsmall/onnx/decoder_model.onnx +3 -0
  2. rinna/japanese-gpt2-xsmall/onnx/decoder_model_merged.onnx +3 -0
  3. rinna/japanese-gpt2-xsmall/onnx/decoder_model_merged_quantized.onnx +3 -0
  4. rinna/japanese-gpt2-xsmall/onnx/decoder_model_quantized.onnx +3 -0
  5. rinna/japanese-gpt2-xsmall/onnx/decoder_with_past_model.onnx +3 -0
  6. rinna/japanese-gpt2-xsmall/onnx/decoder_with_past_model_quantized.onnx +3 -0
  7. rinna/japanese-gpt2-xsmall/quantize_config.json +97 -0
  8. rinna/japanese-gpt2-xsmall/special_tokens_map.json +9 -0
  9. rinna/japanese-gpt2-xsmall/spiece.model +3 -0
  10. rinna/japanese-gpt2-xsmall/tokenizer.json +0 -0
  11. rinna/japanese-gpt2-xsmall/tokenizer_config.json +17 -0
rinna/japanese-gpt2-xsmall/onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d501515c5bc590be079b3fe8927bebf1c9c9ce85b5cbf154e6af22c8dd77dc5
3
+ size 150877859
rinna/japanese-gpt2-xsmall/onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f07da4d6ec947af2fe28f04e2c14930d3d5d7860f7da325add4a6b62b6f622f7
3
+ size 152167370
rinna/japanese-gpt2-xsmall/onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80fa5977036a077c9b1f7fbd7696ec9fd73b8120c0a13082664349282b0e59a9
3
+ size 40340064
rinna/japanese-gpt2-xsmall/onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c60c182fc66d723c1f45816b827f22fbbb2e759fe32daf9e66499c28b2c15f4e
3
+ size 38930961
rinna/japanese-gpt2-xsmall/onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a92ccb322e4246bc225e8010a66781b4503fa58d2eaf7dd630ef2f01a9fb7ba
3
+ size 150881719
rinna/japanese-gpt2-xsmall/onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ef0770377761eb6f0345037b47d73faf8163f496df3c02999bdf5df7ba9ce9f
3
+ size 38936124
rinna/japanese-gpt2-xsmall/quantize_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model_merged": {
6
+ "op_types": [
7
+ "If",
8
+ "Mul",
9
+ "Sqrt",
10
+ "Tanh",
11
+ "Gemm",
12
+ "Div",
13
+ "Pow",
14
+ "Sub",
15
+ "Unsqueeze",
16
+ "Softmax",
17
+ "Slice",
18
+ "Squeeze",
19
+ "Range",
20
+ "Where",
21
+ "Add",
22
+ "ConstantOfShape",
23
+ "Split",
24
+ "ReduceMean",
25
+ "Cast",
26
+ "Gather",
27
+ "Transpose",
28
+ "MatMul",
29
+ "Reshape",
30
+ "Concat",
31
+ "Shape",
32
+ "Constant"
33
+ ],
34
+ "weight_type": "QInt8"
35
+ },
36
+ "decoder_model": {
37
+ "op_types": [
38
+ "Mul",
39
+ "Sqrt",
40
+ "Tanh",
41
+ "Gemm",
42
+ "Div",
43
+ "Pow",
44
+ "Sub",
45
+ "Unsqueeze",
46
+ "Softmax",
47
+ "Slice",
48
+ "Squeeze",
49
+ "Range",
50
+ "Where",
51
+ "Add",
52
+ "ConstantOfShape",
53
+ "Split",
54
+ "ReduceMean",
55
+ "Cast",
56
+ "Gather",
57
+ "Transpose",
58
+ "MatMul",
59
+ "Reshape",
60
+ "Concat",
61
+ "Shape",
62
+ "Constant"
63
+ ],
64
+ "weight_type": "QInt8"
65
+ },
66
+ "decoder_with_past_model": {
67
+ "op_types": [
68
+ "Mul",
69
+ "Sqrt",
70
+ "Tanh",
71
+ "Gemm",
72
+ "Div",
73
+ "Pow",
74
+ "Sub",
75
+ "Unsqueeze",
76
+ "Softmax",
77
+ "Slice",
78
+ "Squeeze",
79
+ "Range",
80
+ "Where",
81
+ "Add",
82
+ "ConstantOfShape",
83
+ "Split",
84
+ "ReduceMean",
85
+ "Cast",
86
+ "Gather",
87
+ "Transpose",
88
+ "MatMul",
89
+ "Reshape",
90
+ "Concat",
91
+ "Shape",
92
+ "Constant"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ }
96
+ }
97
+ }
rinna/japanese-gpt2-xsmall/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "</s>",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "<unk>"
9
+ }
rinna/japanese-gpt2-xsmall/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5cbdfa8aa7c54c8c5af85b78c309c54a5f2749a20468bf6f60eee007fe6fec1
3
+ size 805634
rinna/japanese-gpt2-xsmall/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
rinna/japanese-gpt2-xsmall/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [],
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": true,
7
+ "eos_token": "</s>",
8
+ "extra_ids": 0,
9
+ "legacy": true,
10
+ "mask_token": "[MASK]",
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "sp_model_kwargs": {},
15
+ "tokenizer_class": "T5Tokenizer",
16
+ "unk_token": "<unk>"
17
+ }