Xenova HF staff commited on
Commit
90ed62e
1 Parent(s): 9674eac

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -25,7 +25,7 @@
25
  "summary_proj_to_labels": true,
26
  "summary_type": "cls_index",
27
  "summary_use_proj": true,
28
- "transformers_version": "4.29.2",
29
  "use_cache": false,
30
  "vocab_size": 50258
31
  }
 
25
  "summary_proj_to_labels": true,
26
  "summary_type": "cls_index",
27
  "summary_use_proj": true,
28
+ "transformers_version": "4.33.0.dev0",
29
  "use_cache": false,
30
  "vocab_size": 50258
31
  }
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 sha256:9d0c146c6685128082c6bda07a1f282173b3d1d1cd88da5ebeb7ab9800afbf62
3
- size 1247366820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a99a231b8a22a1f402c6583f803380062c514a44064202e2e8b7ec2a566bbf89
3
+ size 1028642499
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ece03bf266aeebfaa7443a6b1407ed691c0847a3eded5532e78ec6b3af639a0
3
- size 1247911554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae2f16345fbce32265ff480f7eeb495876009558c36b8f18df26222aa221fa0
3
+ size 1033379856
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f1d3ea9ddd90714ffaed4c9802d5180ce6f60cbda07cc1e2809082262acc162
3
- size 318018578
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c223b1e05ad637eb36a858a336a6f0e64e2de373d7416ee9a7d42228a71226bf
3
+ size 266589262
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:042ac11cfd8cf883c7e2f78f8e8016a9cf141b7b4a8ec47b4b4d543b4032be65
3
- size 317201341
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638646a1d7305a136fc1f425f462b2adfb9ceb8e072904af47aa7801edcfb24d
3
+ size 261580710
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27b1b45c132dbc07666091dd94713a3edb392e1502e4b2d90713a6fcc245aaf2
3
- size 1247374623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f87c69f6ff5915e9918216a2a8ba89f3d226621ddbfe74062782dee3ef1432aa
3
+ size 1028650304
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8aab704b43ee7838c336ad96d38eab71c3f1a27e1b024d1bec01d2e125c38014
3
- size 317211702
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d0c85b35fc50e18ace78d839b5de103d6368a8507e2722ad63a3bac7e15a155
3
+ size 261591073
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
+ "Add",
8
+ "Erf",
9
+ "Mul",
10
+ "Constant",
11
+ "Sqrt",
12
+ "Gemm",
13
+ "Split",
14
+ "Where",
15
+ "Transpose",
16
+ "Sub",
17
+ "Gather",
18
+ "ConstantOfShape",
19
+ "Slice",
20
+ "Pow",
21
+ "ReduceMean",
22
+ "Concat",
23
+ "Cast",
24
+ "Squeeze",
25
+ "Shape",
26
+ "Range",
27
+ "MatMul",
28
+ "Reshape",
29
+ "Unsqueeze",
30
+ "Softmax",
31
+ "Div"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model_merged": {
36
+ "op_types": [
37
+ "Add",
38
+ "Erf",
39
+ "Mul",
40
+ "Constant",
41
+ "Sqrt",
42
+ "Gemm",
43
+ "Split",
44
+ "Where",
45
+ "Transpose",
46
+ "Sub",
47
+ "Gather",
48
+ "ConstantOfShape",
49
+ "Slice",
50
+ "Pow",
51
+ "ReduceMean",
52
+ "Concat",
53
+ "Cast",
54
+ "Squeeze",
55
+ "Shape",
56
+ "Range",
57
+ "MatMul",
58
+ "If",
59
+ "Reshape",
60
+ "Unsqueeze",
61
+ "Softmax",
62
+ "Div"
63
+ ],
64
+ "weight_type": "QInt8"
65
+ },
66
+ "decoder_with_past_model": {
67
+ "op_types": [
68
+ "Add",
69
+ "Erf",
70
+ "Mul",
71
+ "Constant",
72
+ "Sqrt",
73
+ "Gemm",
74
+ "Split",
75
+ "Where",
76
+ "Transpose",
77
+ "Sub",
78
+ "Gather",
79
+ "ConstantOfShape",
80
+ "Slice",
81
+ "Pow",
82
+ "ReduceMean",
83
+ "Concat",
84
+ "Cast",
85
+ "Squeeze",
86
+ "Shape",
87
+ "Range",
88
+ "MatMul",
89
+ "Reshape",
90
+ "Unsqueeze",
91
+ "Softmax",
92
+ "Div"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ }
96
+ }
97
+ }