Xenova HF staff commited on
Commit
044d00e
1 Parent(s): 8e6e47c

Upload folder using huggingface_hub

Browse files
Constant_6_attr__value ADDED
Binary file (65.6 kB). View file
 
config.json CHANGED
@@ -20,7 +20,6 @@
20
  "output_past": true,
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
- "torch_dtype": "float32",
24
  "transformers_version": "4.37.2",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
 
20
  "output_past": true,
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
 
23
  "transformers_version": "4.37.2",
24
  "type_vocab_size": 1,
25
  "use_cache": true,
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d89a0010dd39aa2cfa8b22bb49f06904c5bbf5877135f877da419480f40cde3
3
+ size 607298
onnx/model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eebfb28493f67bba03ce0ef64bfdc7fc5a3bd9d7493f818bb1d78cd798416b4
3
+ size 2266820608
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0826f8c1ab9edf1801db86c61919d4d108e8bfc0b809ec823ad366882ff0b77d
3
+ size 569694530
quantize_config.json CHANGED
@@ -4,34 +4,31 @@
4
  "per_model_config": {
5
  "model": {
6
  "op_types": [
7
- "Concat",
 
 
 
 
 
8
  "ConstantOfShape",
9
- "Erf",
10
- "Mul",
11
- "Shape",
12
  "Pow",
13
- "Cast",
14
- "Sqrt",
15
- "Add",
16
- "Gather",
17
- "Not",
18
- "CumSum",
19
- "Abs",
20
- "Slice",
21
- "Where",
22
- "Transpose",
23
- "Div",
24
  "Softmax",
25
- "Reshape",
 
26
  "Sub",
27
- "MatMul",
28
- "ReduceMean",
29
- "Constant",
30
- "Clip",
31
- "Expand",
32
  "Unsqueeze",
 
 
 
 
 
 
33
  "Equal",
34
- "ReduceSum"
 
 
 
 
35
  ],
36
  "weight_type": "QInt8"
37
  }
 
4
  "per_model_config": {
5
  "model": {
6
  "op_types": [
7
+ "ReduceMean",
8
+ "Where",
9
+ "MatMul",
10
+ "Reshape",
11
+ "Gather",
12
+ "Cast",
13
  "ConstantOfShape",
 
 
 
14
  "Pow",
 
 
 
 
 
 
 
 
 
 
 
15
  "Softmax",
16
+ "Mul",
17
+ "Erf",
18
  "Sub",
 
 
 
 
 
19
  "Unsqueeze",
20
+ "Div",
21
+ "Sqrt",
22
+ "Expand",
23
+ "Add",
24
+ "Transpose",
25
+ "Shape",
26
  "Equal",
27
+ "Not",
28
+ "Constant",
29
+ "Slice",
30
+ "CumSum",
31
+ "Concat"
32
  ],
33
  "weight_type": "QInt8"
34
  }