Xenova HF staff commited on
Commit
4809216
1 Parent(s): bc4f330

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 sha256:41ca8a73fcd906c1ca27ebe16518f6d157fd370d8bce7a48561fcb5a3782e078
3
+ size 30291205
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcab9fdb17fc31628fa7c24511af242398b768d6e56a467e7550ad1494ff5817
3
+ size 30291224
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71dfa676bdc3cf9c27e99cd6d8fc3e008395298c37d0c71f2a08ad5b0889cb46
3
+ size 15229540
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:911e6974ac72a1832001c523f72a31868221a4df61e267d3af66b312999de6e4
3
+ size 7990828
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcab9fdb17fc31628fa7c24511af242398b768d6e56a467e7550ad1494ff5817
3
+ size 30291224
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b7eedc19c26cf4add67d6947c073fd951d4c8617a147ed0d19270fbb00f16a7
3
+ size 7990868
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b7eedc19c26cf4add67d6947c073fd951d4c8617a147ed0d19270fbb00f16a7
3
+ size 7990868
quantize_config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fp16": {},
3
+ "q8": {
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Add",
8
+ "BatchNormalization",
9
+ "Constant",
10
+ "Conv",
11
+ "Div",
12
+ "Erf",
13
+ "Flatten",
14
+ "Gemm",
15
+ "GlobalAveragePool",
16
+ "Identity",
17
+ "Mul",
18
+ "ReduceMean",
19
+ "Relu",
20
+ "Sigmoid",
21
+ "Sub"
22
+ ],
23
+ "weight_type": "QUInt8"
24
+ }
25
+ },
26
+ "per_channel": false,
27
+ "reduce_range": false
28
+ },
29
+ "int8": {
30
+ "per_model_config": {
31
+ "model": {
32
+ "op_types": [
33
+ "Add",
34
+ "BatchNormalization",
35
+ "Constant",
36
+ "Conv",
37
+ "Div",
38
+ "Erf",
39
+ "Flatten",
40
+ "Gemm",
41
+ "GlobalAveragePool",
42
+ "Identity",
43
+ "Mul",
44
+ "ReduceMean",
45
+ "Relu",
46
+ "Sigmoid",
47
+ "Sub"
48
+ ],
49
+ "weight_type": "QInt8"
50
+ }
51
+ },
52
+ "per_channel": false,
53
+ "reduce_range": false
54
+ },
55
+ "uint8": {
56
+ "per_model_config": {
57
+ "model": {
58
+ "op_types": [
59
+ "Add",
60
+ "BatchNormalization",
61
+ "Constant",
62
+ "Conv",
63
+ "Div",
64
+ "Erf",
65
+ "Flatten",
66
+ "Gemm",
67
+ "GlobalAveragePool",
68
+ "Identity",
69
+ "Mul",
70
+ "ReduceMean",
71
+ "Relu",
72
+ "Sigmoid",
73
+ "Sub"
74
+ ],
75
+ "weight_type": "QUInt8"
76
+ }
77
+ },
78
+ "per_channel": false,
79
+ "reduce_range": false
80
+ },
81
+ "q4": {
82
+ "block_size": 32,
83
+ "is_symmetric": true,
84
+ "accuracy_level": null
85
+ },
86
+ "bnb4": {
87
+ "block_size": 64,
88
+ "quant_type": 1
89
+ }
90
+ }