Xenova HF staff commited on
Commit
d950ab2
1 Parent(s): 4dda2d6

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -31,7 +31,7 @@
31
  "summary_proj_to_labels": true,
32
  "summary_type": "cls_index",
33
  "summary_use_proj": true,
34
- "transformers_version": "4.32.0.dev0",
35
  "use_cache": true,
36
  "validate_runner_input": true,
37
  "vocab_size": 49152
 
31
  "summary_proj_to_labels": true,
32
  "summary_type": "cls_index",
33
  "summary_use_proj": true,
34
+ "transformers_version": "4.33.0.dev0",
35
  "use_cache": true,
36
  "validate_runner_input": true,
37
  "vocab_size": 49152
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
  "eos_token_id": 0,
5
- "transformers_version": "4.32.0.dev0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
  "eos_token_id": 0,
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 sha256:643931216abb94822898e27f1b5397aa83fb6833f2a52ebacc7f6fb93ce9c547
3
- size 67546228
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7fa4339e6fa7e8d8c01bbf0ce8cfab864ef49c86240f27e3ec8b7fda4d36e55
3
+ size 67546220
onnx/decoder_model.onnx_data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6769e4ec8861f12edc9919154f528bf52bdc9be056d268e643efcc87c841228c
3
- size 4951482368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4dd1f64315d631f2c367b65a7a9f1f1b402e6e535a503e10fd9b78be19a4c42
3
+ size 4548829184
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a489327c49884dfe17ec8bb9bec0e58524f333cf8529438dd74e579b51cd2e4d
3
- size 135080712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5383a3b4503a86afe2fe04e9a2cfa8f58b930400e13a3de5799f6f66b0b19280
3
+ size 135080792
onnx/decoder_model_merged.onnx_data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6769e4ec8861f12edc9919154f528bf52bdc9be056d268e643efcc87c841228c
3
- size 4951482368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4dd1f64315d631f2c367b65a7a9f1f1b402e6e535a503e10fd9b78be19a4c42
3
+ size 4548829184
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d824f8f3448d776ec974775ff68ded9a73b05b26eb3b422c0cbeaa67e1b021d
3
- size 1377075517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a0478e20af3196737b57d244727164d240999e120d9c655cd58753a86c7b41
3
+ size 1274414053
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe76860084f806c05370701a347431f18df17ab49eb67a0a14b42d9a7d6c04b3
3
- size 1309295033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c842cafd14b3fc28a2df71062aed8ade839bfd86e3b625c9a42895d8d4b9dcc3
3
+ size 1206633937
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:563ca1fc5cb0673dce149a58e004c79346125c4ba094ad523fc2195ec02d58d6
3
- size 67557879
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30957f8e32351b5e995fb8395c8198abc4cf0c381dc98a6fec7b589d58432a30
3
+ size 67557861
onnx/decoder_with_past_model.onnx_data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6769e4ec8861f12edc9919154f528bf52bdc9be056d268e643efcc87c841228c
3
- size 4951482368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4dd1f64315d631f2c367b65a7a9f1f1b402e6e535a503e10fd9b78be19a4c42
3
+ size 4548829184
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84d5609cfbf1787adfa3da0f1910ca833519822ba6b75ee28c3e88193e12d148
3
- size 1309305555
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb8aba9b262675028ae82725272a01a8a07bbd429340ad22c5b0993644c304a
3
+ size 1206644459
quantize_config.json CHANGED
@@ -1,98 +1,98 @@
1
  {
2
- "per_channel": true,
3
- "reduce_range": true,
4
  "per_model_config": {
5
- "decoder_with_past_model": {
6
  "op_types": [
7
- "Gather",
8
- "Squeeze",
9
- "Mul",
10
- "Cast",
11
- "Sub",
12
- "Constant",
13
- "Unsqueeze",
14
- "Tanh",
15
- "Add",
16
- "Softmax",
17
- "Sqrt",
18
- "Where",
19
  "MatMul",
20
- "Shape",
21
  "Slice",
22
- "Concat",
23
- "Div",
 
24
  "Pow",
25
- "And",
26
- "Equal",
27
  "Split",
 
 
 
 
 
 
 
28
  "Transpose",
29
- "ConstantOfShape",
 
 
 
30
  "Reshape",
31
- "CumSum",
32
- "ReduceMean"
 
 
 
 
33
  ],
34
  "weight_type": "QInt8"
35
  },
36
- "decoder_model": {
37
  "op_types": [
38
- "Gather",
39
- "Squeeze",
40
- "Mul",
41
- "Cast",
42
- "Sub",
43
- "Constant",
44
- "Unsqueeze",
45
- "Tanh",
46
- "Add",
47
- "Softmax",
48
- "Sqrt",
49
- "Where",
50
  "MatMul",
51
- "Shape",
52
  "Slice",
53
- "Concat",
54
- "Div",
 
55
  "Pow",
56
- "And",
57
- "Equal",
58
  "Split",
 
 
 
 
 
 
 
59
  "Transpose",
60
- "ConstantOfShape",
 
 
 
 
61
  "Reshape",
62
- "CumSum",
63
- "ReduceMean"
 
 
 
 
64
  ],
65
  "weight_type": "QInt8"
66
  },
67
- "decoder_model_merged": {
68
  "op_types": [
69
- "Gather",
70
- "Squeeze",
71
- "Mul",
72
- "Cast",
73
- "Sub",
74
- "If",
75
- "Constant",
76
- "Unsqueeze",
77
- "Tanh",
78
- "Add",
79
- "Softmax",
80
- "Sqrt",
81
- "Where",
82
  "MatMul",
83
- "Shape",
84
  "Slice",
85
- "Concat",
86
- "Div",
 
87
  "Pow",
88
- "And",
89
- "Equal",
90
  "Split",
 
 
 
 
 
 
 
91
  "Transpose",
92
- "ConstantOfShape",
 
 
 
93
  "Reshape",
94
- "CumSum",
95
- "ReduceMean"
 
 
 
 
96
  ],
97
  "weight_type": "QInt8"
98
  }
 
1
  {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
  "per_model_config": {
5
+ "decoder_model": {
6
  "op_types": [
 
 
 
 
 
 
 
 
 
 
 
 
7
  "MatMul",
 
8
  "Slice",
9
+ "Softmax",
10
+ "Constant",
11
+ "Sub",
12
  "Pow",
 
 
13
  "Split",
14
+ "CumSum",
15
+ "Shape",
16
+ "Mul",
17
+ "And",
18
+ "Div",
19
+ "Gather",
20
+ "Sqrt",
21
  "Transpose",
22
+ "Where",
23
+ "ReduceMean",
24
+ "Unsqueeze",
25
+ "Squeeze",
26
  "Reshape",
27
+ "Equal",
28
+ "ConstantOfShape",
29
+ "Concat",
30
+ "Tanh",
31
+ "Cast",
32
+ "Add"
33
  ],
34
  "weight_type": "QInt8"
35
  },
36
+ "decoder_model_merged": {
37
  "op_types": [
 
 
 
 
 
 
 
 
 
 
 
 
38
  "MatMul",
 
39
  "Slice",
40
+ "Softmax",
41
+ "Constant",
42
+ "Sub",
43
  "Pow",
 
 
44
  "Split",
45
+ "CumSum",
46
+ "Shape",
47
+ "Mul",
48
+ "And",
49
+ "Div",
50
+ "Gather",
51
+ "Sqrt",
52
  "Transpose",
53
+ "If",
54
+ "Where",
55
+ "ReduceMean",
56
+ "Unsqueeze",
57
+ "Squeeze",
58
  "Reshape",
59
+ "Equal",
60
+ "ConstantOfShape",
61
+ "Concat",
62
+ "Tanh",
63
+ "Cast",
64
+ "Add"
65
  ],
66
  "weight_type": "QInt8"
67
  },
68
+ "decoder_with_past_model": {
69
  "op_types": [
 
 
 
 
 
 
 
 
 
 
 
 
 
70
  "MatMul",
 
71
  "Slice",
72
+ "Softmax",
73
+ "Constant",
74
+ "Sub",
75
  "Pow",
 
 
76
  "Split",
77
+ "CumSum",
78
+ "Shape",
79
+ "Mul",
80
+ "And",
81
+ "Div",
82
+ "Gather",
83
+ "Sqrt",
84
  "Transpose",
85
+ "Where",
86
+ "ReduceMean",
87
+ "Unsqueeze",
88
+ "Squeeze",
89
  "Reshape",
90
+ "Equal",
91
+ "ConstantOfShape",
92
+ "Concat",
93
+ "Tanh",
94
+ "Cast",
95
+ "Add"
96
  ],
97
  "weight_type": "QInt8"
98
  }