p1atdev commited on
Commit
5a8886a
1 Parent(s): 3d62e6b

Upload 2 files

Browse files
Files changed (2) hide show
  1. model_quantized.onnx +3 -0
  2. ort_config.json +35 -0
model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:428f264d8b93b8f099afc220826a866d62db5aa1730a49ec1f8e8d8984478fe0
3
+ size 115679339
ort_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "one_external_file": true,
3
+ "opset": null,
4
+ "optimization": {},
5
+ "optimum_version": "1.19.1",
6
+ "quantization": {
7
+ "activations_dtype": "QUInt8",
8
+ "activations_symmetric": false,
9
+ "format": "QOperator",
10
+ "is_static": false,
11
+ "mode": "IntegerOps",
12
+ "nodes_to_exclude": [],
13
+ "nodes_to_quantize": [],
14
+ "operators_to_quantize": [
15
+ "Conv",
16
+ "MatMul",
17
+ "Attention",
18
+ "LSTM",
19
+ "Gather",
20
+ "Transpose",
21
+ "EmbedLayerNormalization"
22
+ ],
23
+ "per_channel": false,
24
+ "qdq_add_pair_to_weight": false,
25
+ "qdq_dedicated_pair": false,
26
+ "qdq_op_type_per_channel_support_to_axis": {
27
+ "MatMul": 1
28
+ },
29
+ "reduce_range": false,
30
+ "weights_dtype": "QInt8",
31
+ "weights_symmetric": true
32
+ },
33
+ "transformers_version": "4.38.2",
34
+ "use_external_data_format": false
35
+ }