Mihaiii commited on
Commit
f26dd05
1 Parent(s): d396966

Upload 8 files

Browse files
config.json CHANGED
@@ -17,7 +17,6 @@
17
  "num_hidden_layers": 3,
18
  "pad_token_id": 0,
19
  "position_embedding_type": "absolute",
20
- "torch_dtype": "float32",
21
  "transformers_version": "4.40.1",
22
  "type_vocab_size": 2,
23
  "use_cache": true,
 
17
  "num_hidden_layers": 3,
18
  "pad_token_id": 0,
19
  "position_embedding_type": "absolute",
 
20
  "transformers_version": "4.40.1",
21
  "type_vocab_size": 2,
22
  "use_cache": true,
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e902e7a8cee38fef914920d1a2abe67496b43f5f42497bad593dcde3a6bab7
3
+ size 69035106
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27fb89c260980d7ce2ab5f85fe1cbdc5c23146fdb6b16107586fa804d1094e37
3
+ size 17452601
quantize_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Shape",
8
+ "Cast",
9
+ "Pow",
10
+ "MatMul",
11
+ "Transpose",
12
+ "Erf",
13
+ "Reshape",
14
+ "Constant",
15
+ "Gather",
16
+ "Softmax",
17
+ "Unsqueeze",
18
+ "Concat",
19
+ "Div",
20
+ "ReduceMean",
21
+ "Sqrt",
22
+ "Sub",
23
+ "Mul",
24
+ "Add",
25
+ "Slice"
26
+ ],
27
+ "weight_type": "QInt8"
28
+ }
29
+ }
30
+ }