lebchen commited on
Commit
b292dee
·
verified ·
1 Parent(s): 20b46ed

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:e24f45ee328e59f55b9b02e2f989e3eb6056d47d5e7ea86e8e62e2d97be40372
3
+ size 709244796
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af59580c3333e46563ecd5c34ad5dcfc2544dec01df547a9af63412459a4342
3
+ size 178440396
onnx/ort_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "one_external_file": true,
3
+ "opset": null,
4
+ "optimization": {},
5
+ "quantization": {
6
+ "activations_dtype": "QUInt8",
7
+ "activations_symmetric": false,
8
+ "format": "QOperator",
9
+ "is_static": false,
10
+ "mode": "IntegerOps",
11
+ "nodes_to_exclude": [],
12
+ "nodes_to_quantize": [],
13
+ "operators_to_quantize": [
14
+ "Conv",
15
+ "MatMul",
16
+ "Attention",
17
+ "LSTM",
18
+ "Gather",
19
+ "Transpose",
20
+ "EmbedLayerNormalization"
21
+ ],
22
+ "per_channel": true,
23
+ "qdq_add_pair_to_weight": false,
24
+ "qdq_dedicated_pair": false,
25
+ "qdq_op_type_per_channel_support_to_axis": {
26
+ "MatMul": 1
27
+ },
28
+ "reduce_range": false,
29
+ "weights_dtype": "QInt8",
30
+ "weights_symmetric": true
31
+ },
32
+ "use_external_data_format": false
33
+ }