Hugging Face's logo

Xenova
/
ipt-350m

Text Generation
Transformers.js
ONNX
mpt
custom_code
Model card Files
xet
Community
1
Xenova HF Staff commited on
Commit
20056e4
·
1 Parent(s): 94ec755

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. onnx/decoder_model_merged.onnx +1 -1
  2. onnx/decoder_model_merged_quantized.onnx +2 -2
  3. onnx/decoder_model_quantized.onnx +2 -2
  4. onnx/decoder_with_past_model_quantized.onnx +2 -2
  5. quantize_config.json +54 -54
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e16283f568a32bd8e9f8716e21a5af318e6ba5438b82d76a13265a4661494fc
3
  size 1415934308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f38588d4238680348dbb1c16c15d2bd2a3e7fc219990b9070c957616ae9ebc9f
3
  size 1415934308
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95fdbeec3fc8c6116c41b2153af4de72ca014a3466fa24b1edbf8904af9bae39
3
- size 356700610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5cf4e5190f545d935d86d09be9f9f66fd2912f1f4ea5571e5d67139b83247db
3
+ size 355594162
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54baba9918925344934e39d5ccc30d10bba3da938240fed4a09e072c6323549d
3
- size 355819455
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6177582b8d5a031910420394a9d05ae0c592bf42df68014731d35048eed2255
3
+ size 354713007
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b26ef4475e8a6e5fff3fc6c76ca1a3fc84b7fff75734969f52c83055ce2ff5d
3
- size 355820242
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba993ac31348a0b6dc7567776cb1850bb020a818db5d34013b3a237df6ce56e
3
+ size 354713794
quantize_config.json CHANGED
@@ -1,100 +1,100 @@
1
  {
2
- "per_channel": true,
3
- "reduce_range": true,
4
  "per_model_config": {
5
  "decoder_model": {
6
  "op_types": [
7
- "Or",
 
 
 
8
  "Pow",
9
- "ConstantOfShape",
 
 
 
 
 
10
  "Mul",
 
11
  "Slice",
 
 
12
  "Transpose",
13
- "Erf",
14
  "MatMul",
15
- "Cast",
 
16
  "Constant",
17
  "ScatterND",
18
- "Sub",
19
- "Unsqueeze",
20
- "Range",
21
- "Add",
22
- "Equal",
23
- "Concat",
24
- "ReduceMean",
25
- "Where",
26
- "Less",
27
- "Div",
28
  "Expand",
29
  "Reshape",
30
- "Not",
31
- "Shape",
32
- "Gather",
33
  "Sqrt",
34
- "Softmax"
 
 
35
  ],
36
  "weight_type": "QInt8"
37
  },
38
  "decoder_model_merged": {
39
  "op_types": [
40
- "Or",
 
 
 
41
  "Pow",
42
- "ConstantOfShape",
 
 
 
 
 
43
  "Mul",
44
  "Slice",
 
 
 
45
  "Transpose",
46
- "Erf",
47
  "MatMul",
48
- "Cast",
 
49
  "Constant",
50
  "ScatterND",
51
- "Sub",
52
- "Unsqueeze",
53
- "Range",
54
- "Add",
55
- "Equal",
56
- "Concat",
57
- "ReduceMean",
58
- "Where",
59
- "Less",
60
- "Div",
61
  "Expand",
62
  "Reshape",
63
- "Not",
64
- "Shape",
65
  "If",
66
- "Gather",
67
  "Sqrt",
68
- "Softmax"
 
 
69
  ],
70
  "weight_type": "QInt8"
71
  },
72
  "decoder_with_past_model": {
73
  "op_types": [
 
 
 
74
  "Pow",
75
- "ConstantOfShape",
 
 
 
 
 
76
  "Mul",
77
  "Slice",
 
78
  "Transpose",
79
- "Erf",
80
  "MatMul",
81
- "Cast",
 
82
  "Constant",
83
- "Sub",
84
- "Unsqueeze",
85
- "Add",
86
- "Equal",
87
- "Concat",
88
- "ReduceMean",
89
- "Where",
90
- "Div",
91
- "Reshape",
92
  "Expand",
93
- "Not",
94
- "Shape",
95
- "Gather",
96
  "Sqrt",
97
- "Softmax"
 
 
98
  ],
99
  "weight_type": "QInt8"
100
  }
 
1
  {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
  "per_model_config": {
5
  "decoder_model": {
6
  "op_types": [
7
+ "Cast",
8
+ "Sub",
9
+ "Div",
10
+ "ReduceMean",
11
  "Pow",
12
+ "Erf",
13
+ "Gather",
14
+ "Less",
15
+ "Add",
16
+ "Where",
17
+ "Equal",
18
  "Mul",
19
+ "Or",
20
  "Slice",
21
+ "Range",
22
+ "ConstantOfShape",
23
  "Transpose",
 
24
  "MatMul",
25
+ "Softmax",
26
+ "Not",
27
  "Constant",
28
  "ScatterND",
 
 
 
 
 
 
 
 
 
 
29
  "Expand",
30
  "Reshape",
 
 
 
31
  "Sqrt",
32
+ "Unsqueeze",
33
+ "Concat",
34
+ "Shape"
35
  ],
36
  "weight_type": "QInt8"
37
  },
38
  "decoder_model_merged": {
39
  "op_types": [
40
+ "Cast",
41
+ "Sub",
42
+ "Div",
43
+ "ReduceMean",
44
  "Pow",
45
+ "Erf",
46
+ "Gather",
47
+ "Less",
48
+ "Add",
49
+ "Where",
50
+ "Equal",
51
  "Mul",
52
  "Slice",
53
+ "Or",
54
+ "Range",
55
+ "ConstantOfShape",
56
  "Transpose",
 
57
  "MatMul",
58
+ "Softmax",
59
+ "Not",
60
  "Constant",
61
  "ScatterND",
 
 
 
 
 
 
 
 
 
 
62
  "Expand",
63
  "Reshape",
 
 
64
  "If",
 
65
  "Sqrt",
66
+ "Unsqueeze",
67
+ "Concat",
68
+ "Shape"
69
  ],
70
  "weight_type": "QInt8"
71
  },
72
  "decoder_with_past_model": {
73
  "op_types": [
74
+ "Div",
75
+ "Cast",
76
+ "Sub",
77
  "Pow",
78
+ "ReduceMean",
79
+ "Erf",
80
+ "Gather",
81
+ "Add",
82
+ "Where",
83
+ "Equal",
84
  "Mul",
85
  "Slice",
86
+ "ConstantOfShape",
87
  "Transpose",
 
88
  "MatMul",
89
+ "Softmax",
90
+ "Not",
91
  "Constant",
 
 
 
 
 
 
 
 
 
92
  "Expand",
93
+ "Reshape",
 
 
94
  "Sqrt",
95
+ "Unsqueeze",
96
+ "Concat",
97
+ "Shape"
98
  ],
99
  "weight_type": "QInt8"
100
  }