Upload folder using huggingface_hub
Browse files- config.json +1 -1
- generation_config.json +1 -1
- onnx/decoder_model.onnx +2 -2
- onnx/decoder_model_merged.onnx +2 -2
- onnx/decoder_model_merged_quantized.onnx +2 -2
- onnx/decoder_model_quantized.onnx +2 -2
- onnx/decoder_with_past_model.onnx +2 -2
- onnx/decoder_with_past_model_quantized.onnx +2 -2
- quantize_config.json +125 -0
config.json
CHANGED
@@ -70,7 +70,7 @@
|
|
70 |
"num_beams": 4
|
71 |
}
|
72 |
},
|
73 |
-
"transformers_version": "4.
|
74 |
"use_cache": true,
|
75 |
"vocab_size": 50264
|
76 |
}
|
|
|
70 |
"num_beams": 4
|
71 |
}
|
72 |
},
|
73 |
+
"transformers_version": "4.33.0.dev0",
|
74 |
"use_cache": true,
|
75 |
"vocab_size": 50264
|
76 |
}
|
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.
|
16 |
}
|
|
|
12 |
"no_repeat_ngram_size": 3,
|
13 |
"num_beams": 4,
|
14 |
"pad_token_id": 1,
|
15 |
+
"transformers_version": "4.33.0.dev0"
|
16 |
}
|
onnx/decoder_model.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a34147806885ea37601ae6d91a2598a93acc78db07a06e637f2f1e6ef9c90699
|
3 |
+
size 819581461
|
onnx/decoder_model_merged.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c15a6f30dad41c3265f6786dbd850b6c563d9e6cca0197a1517822ccf2cb44b
|
3 |
+
size 819827967
|
onnx/decoder_model_merged_quantized.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06a8b2aad1811a49576bb1fae43142bd91fc90204065a363191268ee84a7cd28
|
3 |
+
size 206825235
|
onnx/decoder_model_quantized.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b704da825ee605a2576a88093fed2442978b00309d3a576337ae2fe1ac843fcf
|
3 |
+
size 206437988
|
onnx/decoder_with_past_model.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:145e78c5a35e7bd92f57f58b17b9538c202ccd2e4b233b8f4deb2d91e3454a32
|
3 |
+
size 769158110
|
onnx/decoder_with_past_model_quantized.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8615325c7835f7734c6c6ed53264dc85f9954db1f176697cf033fc596fc7f52c
|
3 |
+
size 193674668
|
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 |
+
"Cast",
|
8 |
+
"Transpose",
|
9 |
+
"Slice",
|
10 |
+
"Concat",
|
11 |
+
"Unsqueeze",
|
12 |
+
"Where",
|
13 |
+
"Pow",
|
14 |
+
"Expand",
|
15 |
+
"MatMul",
|
16 |
+
"Sub",
|
17 |
+
"Div",
|
18 |
+
"Equal",
|
19 |
+
"Mul",
|
20 |
+
"Gather",
|
21 |
+
"Constant",
|
22 |
+
"Softmax",
|
23 |
+
"Shape",
|
24 |
+
"Squeeze",
|
25 |
+
"ConstantOfShape",
|
26 |
+
"Range",
|
27 |
+
"Less",
|
28 |
+
"Add",
|
29 |
+
"Sqrt",
|
30 |
+
"Reshape",
|
31 |
+
"ReduceMean",
|
32 |
+
"Erf"
|
33 |
+
],
|
34 |
+
"weight_type": "QInt8"
|
35 |
+
},
|
36 |
+
"decoder_model_merged": {
|
37 |
+
"op_types": [
|
38 |
+
"Cast",
|
39 |
+
"If",
|
40 |
+
"Transpose",
|
41 |
+
"Slice",
|
42 |
+
"Concat",
|
43 |
+
"Unsqueeze",
|
44 |
+
"Where",
|
45 |
+
"Pow",
|
46 |
+
"Expand",
|
47 |
+
"MatMul",
|
48 |
+
"Sub",
|
49 |
+
"Div",
|
50 |
+
"Equal",
|
51 |
+
"Mul",
|
52 |
+
"Gather",
|
53 |
+
"Constant",
|
54 |
+
"Softmax",
|
55 |
+
"Shape",
|
56 |
+
"Squeeze",
|
57 |
+
"ConstantOfShape",
|
58 |
+
"Range",
|
59 |
+
"Less",
|
60 |
+
"Add",
|
61 |
+
"Sqrt",
|
62 |
+
"Reshape",
|
63 |
+
"ReduceMean",
|
64 |
+
"Erf"
|
65 |
+
],
|
66 |
+
"weight_type": "QInt8"
|
67 |
+
},
|
68 |
+
"decoder_with_past_model": {
|
69 |
+
"op_types": [
|
70 |
+
"Cast",
|
71 |
+
"Transpose",
|
72 |
+
"Concat",
|
73 |
+
"Unsqueeze",
|
74 |
+
"Where",
|
75 |
+
"Pow",
|
76 |
+
"Expand",
|
77 |
+
"MatMul",
|
78 |
+
"Sub",
|
79 |
+
"Div",
|
80 |
+
"Equal",
|
81 |
+
"Mul",
|
82 |
+
"Gather",
|
83 |
+
"Constant",
|
84 |
+
"Softmax",
|
85 |
+
"Shape",
|
86 |
+
"ConstantOfShape",
|
87 |
+
"Range",
|
88 |
+
"Add",
|
89 |
+
"Sqrt",
|
90 |
+
"Reshape",
|
91 |
+
"ReduceMean",
|
92 |
+
"Erf"
|
93 |
+
],
|
94 |
+
"weight_type": "QInt8"
|
95 |
+
},
|
96 |
+
"encoder_model": {
|
97 |
+
"op_types": [
|
98 |
+
"Cast",
|
99 |
+
"Transpose",
|
100 |
+
"Concat",
|
101 |
+
"Unsqueeze",
|
102 |
+
"Where",
|
103 |
+
"Pow",
|
104 |
+
"Expand",
|
105 |
+
"MatMul",
|
106 |
+
"Sub",
|
107 |
+
"Div",
|
108 |
+
"Equal",
|
109 |
+
"Mul",
|
110 |
+
"Gather",
|
111 |
+
"Constant",
|
112 |
+
"Softmax",
|
113 |
+
"Shape",
|
114 |
+
"ConstantOfShape",
|
115 |
+
"Range",
|
116 |
+
"Add",
|
117 |
+
"Sqrt",
|
118 |
+
"Reshape",
|
119 |
+
"ReduceMean",
|
120 |
+
"Erf"
|
121 |
+
],
|
122 |
+
"weight_type": "QInt8"
|
123 |
+
}
|
124 |
+
}
|
125 |
+
}
|