Xenova HF staff commited on
Commit
4d7743e
1 Parent(s): 5b7a30b

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -35,7 +35,7 @@
35
  },
36
  "tie_word_embeddings": false,
37
  "tokenizer_class": "GPT2Tokenizer",
38
- "transformers_version": "4.29.2",
39
  "use_cache": true,
40
  "vocab_size": 51200
41
  }
 
35
  },
36
  "tie_word_embeddings": false,
37
  "tokenizer_class": "GPT2Tokenizer",
38
+ "transformers_version": "4.33.0.dev0",
39
  "use_cache": true,
40
  "vocab_size": 51200
41
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 50256,
5
- "transformers_version": "4.29.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
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 sha256:4242141d65d534bd672c5e0542233ba4604a20a653a4453f05722a66b45e031c
3
- size 1435433361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7ca1731136b2170d0b8093078145e75aa04c04116e99c5e7fdc683002ae3ec
3
+ size 1435431277
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97c27fbe0d6d01c037754d8774a48351be1d697d3e1dd7fbf1bc22be58eda607
3
- size 1436616704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe8a26f9fe8fada298eaa7665885adbb6f11c70a8bd819404d375618ee0196a9
3
+ size 1440806546
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff668cb349fa948bc190de5b8d90b17599cd81e76d91e4a6de966bc8e2b7e9ab
3
- size 370397206
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a16c55862fbc5b5dc2378fbb30d3a27b859de3671cb18bb3a7a2b80f10d9913
3
+ size 373406721
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:678c3bd5fa56b81452e35d619736e54bd7f5aa210b05b08c37d9487e42cad3e8
3
- size 368793710
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9ad3b1b37811c2f6690e2c4dbaea552bef982d4c8112ff65919c9ae2a7248d
3
+ size 367612429
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e1bbdd8ff34cec0be10cb2353f8c9fd736321f797063a9a805f1e646d7b3953
3
- size 1432225419
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0df9500683655b4668f44f7c01034b38f570dc0757bdd8a757267468a155c77a
3
+ size 1432223346
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e098dcf05ece0193328253da6080965be819aca75a33d874471f5249f09f744
3
- size 364276590
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c41d0e7eb89997fefc8e122cd34633f7a9600d7419a9658c278200e12fc35cb5
3
+ size 363095324
quantize_config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Cast",
8
+ "Equal",
9
+ "Sqrt",
10
+ "Softmax",
11
+ "Neg",
12
+ "Reshape",
13
+ "ReduceMean",
14
+ "Where",
15
+ "MatMul",
16
+ "Slice",
17
+ "Shape",
18
+ "Unsqueeze",
19
+ "Gather",
20
+ "Sub",
21
+ "Squeeze",
22
+ "Mul",
23
+ "Split",
24
+ "Expand",
25
+ "ConstantOfShape",
26
+ "Concat",
27
+ "Constant",
28
+ "Transpose",
29
+ "Range",
30
+ "Pow",
31
+ "Tanh",
32
+ "Add",
33
+ "Div"
34
+ ],
35
+ "weight_type": "QInt8"
36
+ },
37
+ "decoder_model_merged": {
38
+ "op_types": [
39
+ "Cast",
40
+ "Equal",
41
+ "Sqrt",
42
+ "Softmax",
43
+ "Neg",
44
+ "Reshape",
45
+ "ReduceMean",
46
+ "Where",
47
+ "MatMul",
48
+ "Slice",
49
+ "Shape",
50
+ "Gather",
51
+ "Unsqueeze",
52
+ "Sub",
53
+ "Squeeze",
54
+ "Mul",
55
+ "Split",
56
+ "Expand",
57
+ "ConstantOfShape",
58
+ "Concat",
59
+ "Constant",
60
+ "Transpose",
61
+ "Range",
62
+ "Pow",
63
+ "Tanh",
64
+ "Add",
65
+ "If",
66
+ "Div"
67
+ ],
68
+ "weight_type": "QInt8"
69
+ },
70
+ "decoder_with_past_model": {
71
+ "op_types": [
72
+ "Cast",
73
+ "Equal",
74
+ "Sqrt",
75
+ "Softmax",
76
+ "Neg",
77
+ "Reshape",
78
+ "ReduceMean",
79
+ "Where",
80
+ "MatMul",
81
+ "Slice",
82
+ "Shape",
83
+ "Unsqueeze",
84
+ "Gather",
85
+ "Sub",
86
+ "Squeeze",
87
+ "Mul",
88
+ "Split",
89
+ "Expand",
90
+ "ConstantOfShape",
91
+ "Concat",
92
+ "Constant",
93
+ "Transpose",
94
+ "Range",
95
+ "Pow",
96
+ "Tanh",
97
+ "Add",
98
+ "Div"
99
+ ],
100
+ "weight_type": "QInt8"
101
+ }
102
+ }
103
+ }