Xenova HF staff commited on
Commit
9a68bf2
1 Parent(s): b9699f3

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -63,7 +63,7 @@
63
  "num_beams": 4
64
  }
65
  },
66
- "transformers_version": "4.29.2",
67
  "use_cache": true,
68
  "vocab_size": 50264
69
  }
 
63
  "num_beams": 4
64
  }
65
  },
66
+ "transformers_version": "4.34.0.dev0",
67
  "use_cache": true,
68
  "vocab_size": 50264
69
  }
generation_config.json CHANGED
@@ -12,5 +12,5 @@
12
  "no_repeat_ngram_size": 3,
13
  "num_beams": 4,
14
  "pad_token_id": 1,
15
- "transformers_version": "4.29.2"
16
  }
 
12
  "no_repeat_ngram_size": 3,
13
  "num_beams": 4,
14
  "pad_token_id": 1,
15
+ "transformers_version": "4.34.0.dev0"
16
  }
onnx/decoder_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ace1c96cc44f533ae223f5ebb9db35f4c5cf8e0592284e662c5bae667e06444d
3
- size 1222931015
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c6b1e1db55c314a525a1981d87e69f332370dfda38c1616d0842be5b790263
3
+ size 1017091776
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f68d519a785d2458cc515dc6d3a1d439d6e2efa0d859d7e7661429dcbe2701dc
3
- size 1223372254
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c7c9b29bcb80c28b0a8ed7ea5306b2a121985fd3f0ecf53b47f019fe860806
3
+ size 1017574814
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9402d1f0255de4221901a31a6b64c941a427930c57444f994934ccb1e2abaae3
3
- size 309046228
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d747cb8cefbf557f8d3ade8efbd43f9a0a0fbdd6deb7503682071647ee0a7cdc
3
+ size 257435745
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77ab4286473c981329253666bff6763d8b997b322673df9fe0ea86da566bf167
3
- size 308343853
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f1596ac223b3ebfd0dab8b14bcf865550bdf0cd23ea9b535a33208b7e7866a
3
+ size 256677944
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d359d786187e502b60514333fe1d9bb37439467b552136969b6700455744b51
3
- size 1122089918
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f33a93db6d4d0715f99f5ddc29de8f3b08fa9c57407e513d8d22c75e39a8493b
3
+ size 916250419
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9af3c60d51963ce72b6b16fbf0c8586ebc395b7e890e416e476b71603b5c1dd4
3
- size 282825152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e8a8b67b5cc287398e1b018495a82264babe2db2806c18265f63ebd37f4cfe
3
+ size 231158860
quantize_config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Constant",
8
+ "Sub",
9
+ "Expand",
10
+ "ConstantOfShape",
11
+ "ReduceMean",
12
+ "Sqrt",
13
+ "Cast",
14
+ "Reshape",
15
+ "Pow",
16
+ "Range",
17
+ "Softmax",
18
+ "Erf",
19
+ "Shape",
20
+ "Squeeze",
21
+ "Less",
22
+ "Mul",
23
+ "Where",
24
+ "Slice",
25
+ "Gather",
26
+ "Unsqueeze",
27
+ "Transpose",
28
+ "Add",
29
+ "Concat",
30
+ "MatMul",
31
+ "Div",
32
+ "Equal"
33
+ ],
34
+ "weight_type": "QInt8"
35
+ },
36
+ "encoder_model": {
37
+ "op_types": [
38
+ "Constant",
39
+ "Sub",
40
+ "Expand",
41
+ "ConstantOfShape",
42
+ "ReduceMean",
43
+ "Sqrt",
44
+ "Reshape",
45
+ "Cast",
46
+ "Pow",
47
+ "Range",
48
+ "Softmax",
49
+ "Erf",
50
+ "Shape",
51
+ "Mul",
52
+ "Where",
53
+ "Gather",
54
+ "Unsqueeze",
55
+ "Transpose",
56
+ "Add",
57
+ "Concat",
58
+ "MatMul",
59
+ "Div",
60
+ "Equal"
61
+ ],
62
+ "weight_type": "QInt8"
63
+ },
64
+ "decoder_model_merged": {
65
+ "op_types": [
66
+ "Constant",
67
+ "Sub",
68
+ "Expand",
69
+ "ConstantOfShape",
70
+ "If",
71
+ "ReduceMean",
72
+ "Sqrt",
73
+ "Cast",
74
+ "Reshape",
75
+ "Pow",
76
+ "Range",
77
+ "Softmax",
78
+ "Erf",
79
+ "Shape",
80
+ "Squeeze",
81
+ "Less",
82
+ "Mul",
83
+ "Where",
84
+ "Slice",
85
+ "Gather",
86
+ "Unsqueeze",
87
+ "Transpose",
88
+ "Add",
89
+ "Concat",
90
+ "MatMul",
91
+ "Div",
92
+ "Equal"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ },
96
+ "decoder_with_past_model": {
97
+ "op_types": [
98
+ "Constant",
99
+ "Sub",
100
+ "Expand",
101
+ "ConstantOfShape",
102
+ "ReduceMean",
103
+ "Sqrt",
104
+ "Reshape",
105
+ "Cast",
106
+ "Pow",
107
+ "Range",
108
+ "Softmax",
109
+ "Erf",
110
+ "Shape",
111
+ "Mul",
112
+ "Where",
113
+ "Gather",
114
+ "Unsqueeze",
115
+ "Transpose",
116
+ "Add",
117
+ "Concat",
118
+ "MatMul",
119
+ "Div",
120
+ "Equal"
121
+ ],
122
+ "weight_type": "QInt8"
123
+ }
124
+ }
125
+ }