Hugging Face's logo

tarekziade
/
wikipedia-summaries-t5-efficient-tiny

Transformers
ONNX
Safetensors
t5
text2text-generation
text-generation-inference
Model card Files
xet
Community
tarekziade commited on
Commit
6118c49
·
1 Parent(s): 226ebec

Upload 5 files

Browse files
Files changed (5) hide show
  1. onnx/decoder_model.onnx +3 -0
  2. onnx/decoder_model_quantized.onnx +3 -0
  3. onnx/encoder_model.onnx +3 -0
  4. onnx/encoder_model_quantized.onnx +3 -0
  5. quantize_config.json +70 -0
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8572d63b890614082d4464a91000c170c5a05f7a01e6f2c67f5ed2df3f36a89
3
+ size 49807062
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152bc54ef464edb52ce84c87cdd9a1ee1891395eb38a02189fe54c12a94f839a
3
+ size 12707110
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd0fc830362432cb1fc44ea2af0ac62fde5515bd07e986b31443125d3652eb1
3
+ size 45549185
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8d0687555ef7a606ee36e1dd84d61b65243016240717a04fba41f787fbbfdc7
3
+ size 11531806
quantize_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Gather",
8
+ "Neg",
9
+ "Log",
10
+ "MatMul",
11
+ "Unsqueeze",
12
+ "Reshape",
13
+ "Add",
14
+ "Sub",
15
+ "ConstantOfShape",
16
+ "Relu",
17
+ "Div",
18
+ "Range",
19
+ "Min",
20
+ "Constant",
21
+ "Pow",
22
+ "Expand",
23
+ "Softmax",
24
+ "Mul",
25
+ "LessOrEqual",
26
+ "Less",
27
+ "Where",
28
+ "Transpose",
29
+ "ReduceMean",
30
+ "Shape",
31
+ "Tile",
32
+ "Sqrt",
33
+ "Cast",
34
+ "Concat"
35
+ ],
36
+ "weight_type": "QInt8"
37
+ },
38
+ "encoder_model": {
39
+ "op_types": [
40
+ "Gather",
41
+ "Log",
42
+ "MatMul",
43
+ "Unsqueeze",
44
+ "Reshape",
45
+ "Add",
46
+ "Sub",
47
+ "ConstantOfShape",
48
+ "Relu",
49
+ "Div",
50
+ "Range",
51
+ "Min",
52
+ "Constant",
53
+ "Pow",
54
+ "Greater",
55
+ "Softmax",
56
+ "Mul",
57
+ "Less",
58
+ "Where",
59
+ "Transpose",
60
+ "Abs",
61
+ "ReduceMean",
62
+ "Shape",
63
+ "Sqrt",
64
+ "Cast",
65
+ "Concat"
66
+ ],
67
+ "weight_type": "QInt8"
68
+ }
69
+ }
70
+ }