Xenova HF staff commited on
Commit
5ac8eb1
1 Parent(s): 40ebb55

Upload folder using huggingface_hub

Browse files
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2fcbd6764d2434b969d5851e948e9ccab5779b356f6b586efe696ee6d15380f
3
+ size 1873498357
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:033aeddccff186b769d5b0d5a18a8098b5d550bfafe03dde5986089adb98810e
3
+ size 482326148
quantize_config.json CHANGED
@@ -4,33 +4,33 @@
4
  "per_model_config": {
5
  "model": {
6
  "op_types": [
7
- "ConstantOfShape",
8
- "Where",
9
- "Softmax",
10
- "Add",
11
- "Mul",
12
- "Concat",
13
- "Trilu",
14
- "Constant",
15
- "Shape",
16
- "MatMul",
17
- "Sigmoid",
18
- "Reshape",
19
- "Less",
20
- "Unsqueeze",
21
  "Sub",
22
- "Pow",
23
- "ReduceMean",
24
- "Expand",
25
- "Range",
26
  "Div",
27
- "Squeeze",
28
  "Equal",
 
 
 
 
29
  "Cast",
30
- "Neg",
31
- "Slice",
32
- "Gather",
33
  "Sqrt",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  "Transpose"
35
  ],
36
  "weight_type": "QInt8"
 
4
  "per_model_config": {
5
  "model": {
6
  "op_types": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "Sub",
 
 
 
 
8
  "Div",
9
+ "MatMul",
10
  "Equal",
11
+ "Expand",
12
+ "ReduceMean",
13
+ "Squeeze",
14
+ "Pow",
15
  "Cast",
16
+ "Reshape",
17
+ "Trilu",
18
+ "Where",
19
  "Sqrt",
20
+ "Range",
21
+ "Gather",
22
+ "Unsqueeze",
23
+ "Mul",
24
+ "Sigmoid",
25
+ "Shape",
26
+ "Slice",
27
+ "ConstantOfShape",
28
+ "Softmax",
29
+ "Add",
30
+ "Neg",
31
+ "Constant",
32
+ "Concat",
33
+ "Less",
34
  "Transpose"
35
  ],
36
  "weight_type": "QInt8"