Upload folder using huggingface_hub
Browse files- config.json +2 -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
- onnx/encoder_model.onnx +1 -1
- onnx/encoder_model_quantized.onnx +2 -2
- quantize_config.json +139 -0
- tokenizer_config.json +1 -0
config.json
CHANGED
@@ -3,6 +3,7 @@
|
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
6 |
"d_ff": 2048,
|
7 |
"d_kv": 64,
|
8 |
"d_model": 768,
|
@@ -24,7 +25,7 @@
|
|
24 |
"relative_attention_max_distance": 128,
|
25 |
"relative_attention_num_buckets": 32,
|
26 |
"tie_word_embeddings": false,
|
27 |
-
"transformers_version": "4.
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 32128
|
30 |
}
|
|
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
"d_ff": 2048,
|
8 |
"d_kv": 64,
|
9 |
"d_model": 768,
|
|
|
25 |
"relative_attention_max_distance": 128,
|
26 |
"relative_attention_num_buckets": 32,
|
27 |
"tie_word_embeddings": false,
|
28 |
+
"transformers_version": "4.33.0.dev0",
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 32128
|
31 |
}
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
-
"transformers_version": "4.
|
7 |
}
|
|
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.33.0.dev0"
|
7 |
}
|
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 sha256:5a04194eb823d83980b9a406346af6accddbfc9ab85068918498253423441f60
|
3 |
+
size 650848961
|
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 sha256:53c515e3977d335e82d140c9521ec34a4ab46286600333cd78b1e60093644d50
|
3 |
+
size 651182887
|
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 sha256:5e5c778efa9cb15f68a18c125443bd38f521c0f3553949599fe145acf437822d
|
3 |
+
size 164739632
|
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:b6efcc9a424d07d7e8fd9075bd3c4fb7ea558d608ebf428d4092629d6c784dc3
|
3 |
+
size 164163118
|
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:f4c9d69c4f46e247fbb09b774ed9743a997ad073f13fde1714fa629acfa54d2a
|
3 |
+
size 594197309
|
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 sha256:7fe68a8380083fba399d7983a502d55413315f96c4a45d2f14636c6ddbc8fe72
|
3 |
+
size 149854152
|
onnx/encoder_model.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 438697388
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c1a769e5283d5ef269b1e8a29f8ba597758231cf82e307bf5fe1efa11681074
|
3 |
size 438697388
|
onnx/encoder_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 sha256:3ac4080485da9d051127524c0e375adb109bdd5694a48c96b455b3015046d7bf
|
3 |
+
size 110502358
|
quantize_config.json
ADDED
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"decoder_model": {
|
6 |
+
"op_types": [
|
7 |
+
"Constant",
|
8 |
+
"Where",
|
9 |
+
"Tile",
|
10 |
+
"ConstantOfShape",
|
11 |
+
"Expand",
|
12 |
+
"MatMul",
|
13 |
+
"Unsqueeze",
|
14 |
+
"Range",
|
15 |
+
"Transpose",
|
16 |
+
"Tanh",
|
17 |
+
"ReduceMean",
|
18 |
+
"Cast",
|
19 |
+
"Sqrt",
|
20 |
+
"Add",
|
21 |
+
"Neg",
|
22 |
+
"Min",
|
23 |
+
"Log",
|
24 |
+
"Concat",
|
25 |
+
"Div",
|
26 |
+
"Softmax",
|
27 |
+
"Pow",
|
28 |
+
"Shape",
|
29 |
+
"Gather",
|
30 |
+
"Sub",
|
31 |
+
"LessOrEqual",
|
32 |
+
"Mul",
|
33 |
+
"Reshape",
|
34 |
+
"Less"
|
35 |
+
],
|
36 |
+
"weight_type": "QInt8"
|
37 |
+
},
|
38 |
+
"encoder_model": {
|
39 |
+
"op_types": [
|
40 |
+
"Constant",
|
41 |
+
"Where",
|
42 |
+
"ConstantOfShape",
|
43 |
+
"MatMul",
|
44 |
+
"Unsqueeze",
|
45 |
+
"Range",
|
46 |
+
"Transpose",
|
47 |
+
"Tanh",
|
48 |
+
"ReduceMean",
|
49 |
+
"Cast",
|
50 |
+
"Sqrt",
|
51 |
+
"Greater",
|
52 |
+
"Add",
|
53 |
+
"Abs",
|
54 |
+
"Min",
|
55 |
+
"Log",
|
56 |
+
"Concat",
|
57 |
+
"Div",
|
58 |
+
"Softmax",
|
59 |
+
"Pow",
|
60 |
+
"Shape",
|
61 |
+
"Gather",
|
62 |
+
"Sub",
|
63 |
+
"Mul",
|
64 |
+
"Reshape",
|
65 |
+
"Less"
|
66 |
+
],
|
67 |
+
"weight_type": "QInt8"
|
68 |
+
},
|
69 |
+
"decoder_model_merged": {
|
70 |
+
"op_types": [
|
71 |
+
"Constant",
|
72 |
+
"Where",
|
73 |
+
"Tile",
|
74 |
+
"ConstantOfShape",
|
75 |
+
"Expand",
|
76 |
+
"MatMul",
|
77 |
+
"Unsqueeze",
|
78 |
+
"Range",
|
79 |
+
"Transpose",
|
80 |
+
"Tanh",
|
81 |
+
"ReduceMean",
|
82 |
+
"Cast",
|
83 |
+
"Sqrt",
|
84 |
+
"Slice",
|
85 |
+
"Add",
|
86 |
+
"Neg",
|
87 |
+
"Min",
|
88 |
+
"Log",
|
89 |
+
"Concat",
|
90 |
+
"Div",
|
91 |
+
"Softmax",
|
92 |
+
"Pow",
|
93 |
+
"If",
|
94 |
+
"Shape",
|
95 |
+
"Gather",
|
96 |
+
"Sub",
|
97 |
+
"LessOrEqual",
|
98 |
+
"Mul",
|
99 |
+
"Reshape",
|
100 |
+
"Less"
|
101 |
+
],
|
102 |
+
"weight_type": "QInt8"
|
103 |
+
},
|
104 |
+
"decoder_with_past_model": {
|
105 |
+
"op_types": [
|
106 |
+
"Constant",
|
107 |
+
"Where",
|
108 |
+
"Tile",
|
109 |
+
"ConstantOfShape",
|
110 |
+
"Expand",
|
111 |
+
"MatMul",
|
112 |
+
"Unsqueeze",
|
113 |
+
"Range",
|
114 |
+
"Transpose",
|
115 |
+
"Tanh",
|
116 |
+
"ReduceMean",
|
117 |
+
"Cast",
|
118 |
+
"Sqrt",
|
119 |
+
"Slice",
|
120 |
+
"Add",
|
121 |
+
"Neg",
|
122 |
+
"Min",
|
123 |
+
"Log",
|
124 |
+
"Concat",
|
125 |
+
"Div",
|
126 |
+
"Softmax",
|
127 |
+
"Pow",
|
128 |
+
"Shape",
|
129 |
+
"Gather",
|
130 |
+
"Sub",
|
131 |
+
"LessOrEqual",
|
132 |
+
"Mul",
|
133 |
+
"Reshape",
|
134 |
+
"Less"
|
135 |
+
],
|
136 |
+
"weight_type": "QInt8"
|
137 |
+
}
|
138 |
+
}
|
139 |
+
}
|
tokenizer_config.json
CHANGED
@@ -104,6 +104,7 @@
|
|
104 |
"clean_up_tokenization_spaces": true,
|
105 |
"eos_token": "</s>",
|
106 |
"extra_ids": 100,
|
|
|
107 |
"model_max_length": 512,
|
108 |
"pad_token": "<pad>",
|
109 |
"sp_model_kwargs": {},
|
|
|
104 |
"clean_up_tokenization_spaces": true,
|
105 |
"eos_token": "</s>",
|
106 |
"extra_ids": 100,
|
107 |
+
"legacy": true,
|
108 |
"model_max_length": 512,
|
109 |
"pad_token": "<pad>",
|
110 |
"sp_model_kwargs": {},
|