Xenova HF staff commited on
Commit
f7421df
1 Parent(s): 8ec54aa

Upload folder using huggingface_hub

Browse files
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb6a5c28f3b6bf1618c6e43f02073ef9dfdc70e937502d51603e57b0a1df10c
3
+ size 99060839
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0312c94ffd25c662880df1d55b336f028115166eb574ebc1622901d39e984185
3
+ size 26077648
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df6223f206b5164e21f664ace61dabeb9bb6a49b8b5a3e00510b4807d0f5b04
3
+ size 49642442
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01aa7a23de3f4a0ee1a2bb9997e6918104c85a9f95dea46d27b9b3fb0c6b9001
3
+ size 27258801
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d55b02762e1907589158af3e366bd61ddf648155852a07bbf5e3a074639fcf8
3
+ size 27404416
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcf51f1b230362b28690bb9d1809bf0431f29cad20534e3f589bd7285547f20d
3
+ size 27258801
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcf51f1b230362b28690bb9d1809bf0431f29cad20534e3f589bd7285547f20d
3
+ size 27258801
quantize_config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fp16": {},
3
+ "q8": {
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Add",
8
+ "Concat",
9
+ "Conv",
10
+ "ConvTranspose",
11
+ "Div",
12
+ "Equal",
13
+ "Erf",
14
+ "Expand",
15
+ "Gather",
16
+ "MatMul",
17
+ "Mul",
18
+ "Pow",
19
+ "ReduceMean",
20
+ "Relu",
21
+ "Reshape",
22
+ "Resize",
23
+ "Shape",
24
+ "Slice",
25
+ "Softmax",
26
+ "Sqrt",
27
+ "Squeeze",
28
+ "Sub",
29
+ "Transpose",
30
+ "Unsqueeze",
31
+ "Where"
32
+ ],
33
+ "weight_type": "QUInt8"
34
+ }
35
+ },
36
+ "per_channel": true,
37
+ "reduce_range": true
38
+ },
39
+ "int8": {
40
+ "per_model_config": {
41
+ "model": {
42
+ "op_types": [
43
+ "Add",
44
+ "Concat",
45
+ "Conv",
46
+ "ConvTranspose",
47
+ "Div",
48
+ "Equal",
49
+ "Erf",
50
+ "Expand",
51
+ "Gather",
52
+ "MatMul",
53
+ "Mul",
54
+ "Pow",
55
+ "ReduceMean",
56
+ "Relu",
57
+ "Reshape",
58
+ "Resize",
59
+ "Shape",
60
+ "Slice",
61
+ "Softmax",
62
+ "Sqrt",
63
+ "Squeeze",
64
+ "Sub",
65
+ "Transpose",
66
+ "Unsqueeze",
67
+ "Where"
68
+ ],
69
+ "weight_type": "QInt8"
70
+ }
71
+ },
72
+ "per_channel": true,
73
+ "reduce_range": true
74
+ },
75
+ "uint8": {
76
+ "per_model_config": {
77
+ "model": {
78
+ "op_types": [
79
+ "Add",
80
+ "Concat",
81
+ "Conv",
82
+ "ConvTranspose",
83
+ "Div",
84
+ "Equal",
85
+ "Erf",
86
+ "Expand",
87
+ "Gather",
88
+ "MatMul",
89
+ "Mul",
90
+ "Pow",
91
+ "ReduceMean",
92
+ "Relu",
93
+ "Reshape",
94
+ "Resize",
95
+ "Shape",
96
+ "Slice",
97
+ "Softmax",
98
+ "Sqrt",
99
+ "Squeeze",
100
+ "Sub",
101
+ "Transpose",
102
+ "Unsqueeze",
103
+ "Where"
104
+ ],
105
+ "weight_type": "QUInt8"
106
+ }
107
+ },
108
+ "per_channel": true,
109
+ "reduce_range": true
110
+ },
111
+ "q4": {
112
+ "block_size": 32,
113
+ "is_symmetric": true,
114
+ "accuracy_level": null
115
+ },
116
+ "bnb4": {
117
+ "block_size": 64,
118
+ "quant_type": 1
119
+ }
120
+ }