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 +103 -0
config.json
CHANGED
@@ -35,7 +35,7 @@
|
|
35 |
},
|
36 |
"tie_word_embeddings": false,
|
37 |
"tokenizer_class": "GPT2Tokenizer",
|
38 |
-
"transformers_version": "4.
|
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.
|
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ddd9281192b6a7efbff7d67f0bbc24767ddd0fab00c560313be4a654a5b1b49
|
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53617d55ffdffa28f737c54f400957ed0459145dca8d0352a44a66423a14ac1b
|
3 |
+
size 1440806522
|
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:ccb331ff7b021cbde82a0a2100abdc3245c959c03c31be9f5def260f5b9de077
|
3 |
+
size 373406649
|
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 sha256:27cc1940441e137ead9cea7fa79c5afeb6e31eb740f292831ae59d369ea29616
|
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f49e897e86b729e22fa1bb31b075e23c01e7d4292cd61cd38fdfcd00117f165
|
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5845d0a1fb6c7fe3143d9eec00389a06c81dc4fd8326b55c49b0873a4d721548
|
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 |
+
"Transpose",
|
8 |
+
"Sub",
|
9 |
+
"Cast",
|
10 |
+
"Softmax",
|
11 |
+
"Slice",
|
12 |
+
"ReduceMean",
|
13 |
+
"Squeeze",
|
14 |
+
"Gather",
|
15 |
+
"Range",
|
16 |
+
"Unsqueeze",
|
17 |
+
"Pow",
|
18 |
+
"MatMul",
|
19 |
+
"Add",
|
20 |
+
"Equal",
|
21 |
+
"Concat",
|
22 |
+
"Neg",
|
23 |
+
"Reshape",
|
24 |
+
"Div",
|
25 |
+
"Mul",
|
26 |
+
"Sqrt",
|
27 |
+
"ConstantOfShape",
|
28 |
+
"Where",
|
29 |
+
"Tanh",
|
30 |
+
"Shape",
|
31 |
+
"Expand",
|
32 |
+
"Constant",
|
33 |
+
"Split"
|
34 |
+
],
|
35 |
+
"weight_type": "QInt8"
|
36 |
+
},
|
37 |
+
"decoder_model_merged": {
|
38 |
+
"op_types": [
|
39 |
+
"Transpose",
|
40 |
+
"Sub",
|
41 |
+
"Cast",
|
42 |
+
"Softmax",
|
43 |
+
"Slice",
|
44 |
+
"ReduceMean",
|
45 |
+
"Squeeze",
|
46 |
+
"Gather",
|
47 |
+
"Range",
|
48 |
+
"Unsqueeze",
|
49 |
+
"Pow",
|
50 |
+
"MatMul",
|
51 |
+
"Add",
|
52 |
+
"Equal",
|
53 |
+
"Concat",
|
54 |
+
"If",
|
55 |
+
"Neg",
|
56 |
+
"Reshape",
|
57 |
+
"Div",
|
58 |
+
"Mul",
|
59 |
+
"Sqrt",
|
60 |
+
"ConstantOfShape",
|
61 |
+
"Where",
|
62 |
+
"Tanh",
|
63 |
+
"Shape",
|
64 |
+
"Expand",
|
65 |
+
"Constant",
|
66 |
+
"Split"
|
67 |
+
],
|
68 |
+
"weight_type": "QInt8"
|
69 |
+
},
|
70 |
+
"decoder_with_past_model": {
|
71 |
+
"op_types": [
|
72 |
+
"Transpose",
|
73 |
+
"Sub",
|
74 |
+
"Cast",
|
75 |
+
"Softmax",
|
76 |
+
"Slice",
|
77 |
+
"ReduceMean",
|
78 |
+
"Squeeze",
|
79 |
+
"Gather",
|
80 |
+
"Range",
|
81 |
+
"Unsqueeze",
|
82 |
+
"Pow",
|
83 |
+
"MatMul",
|
84 |
+
"Add",
|
85 |
+
"Equal",
|
86 |
+
"Concat",
|
87 |
+
"Neg",
|
88 |
+
"Reshape",
|
89 |
+
"Div",
|
90 |
+
"Mul",
|
91 |
+
"Sqrt",
|
92 |
+
"ConstantOfShape",
|
93 |
+
"Where",
|
94 |
+
"Tanh",
|
95 |
+
"Shape",
|
96 |
+
"Expand",
|
97 |
+
"Constant",
|
98 |
+
"Split"
|
99 |
+
],
|
100 |
+
"weight_type": "QInt8"
|
101 |
+
}
|
102 |
+
}
|
103 |
+
}
|