Xenova HF staff commited on
Commit
5dbd7e5
·
verified ·
1 Parent(s): d52e5d0

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ _model_layers.0_self_attn_rotary_emb_Constant_5_attr__value filter=lfs diff=lfs merge=lfs -text
37
+ _model_layers.0_self_attn_rotary_emb_Constant_attr__value filter=lfs diff=lfs merge=lfs -text
_model_layers.0_self_attn_rotary_emb_Constant_5_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f44286ec0ca2a407877f4908d4f5607fb5f3a76a9099ee583cc7684dc7de0c
3
+ size 8388608
_model_layers.0_self_attn_rotary_emb_Constant_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e699ce948b3c9fc0b86dc4beb337c5fb1b1edbce5d094aa07c8ae37cd7199f3
3
+ size 8388608
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d63556db976ef2983174f01cc496aa8d90715a81e6c9f130c2965d473984979
3
+ size 1873498357
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:068cad70fa3850652e6ebc0ad7a49847568f32e6eda5a8527e5893de9a7b8939
3
+ size 482326147
quantize_config.json CHANGED
@@ -4,34 +4,34 @@
4
  "per_model_config": {
5
  "model": {
6
  "op_types": [
7
- "Shape",
 
 
 
8
  "Reshape",
9
- "Expand",
10
- "Add",
11
- "Div",
12
- "Equal",
13
- "Where",
14
- "Concat",
15
  "Slice",
 
 
 
16
  "Unsqueeze",
 
 
 
 
17
  "Mul",
 
18
  "Pow",
19
- "Neg",
20
- "Squeeze",
21
- "Constant",
22
- "MatMul",
23
- "Less",
24
- "Gather",
25
- "Cast",
26
- "ReduceMean",
27
- "Sqrt",
28
  "Range",
 
 
 
29
  "Transpose",
30
- "Sigmoid",
31
  "ConstantOfShape",
32
- "Softmax",
33
- "Trilu",
34
- "Sub"
35
  ],
36
  "weight_type": "QInt8"
37
  }
 
4
  "per_model_config": {
5
  "model": {
6
  "op_types": [
7
+ "Less",
8
+ "MatMul",
9
+ "Sqrt",
10
+ "Softmax",
11
  "Reshape",
12
+ "Gather",
 
 
 
 
 
13
  "Slice",
14
+ "Equal",
15
+ "Neg",
16
+ "Sigmoid",
17
  "Unsqueeze",
18
+ "Constant",
19
+ "Expand",
20
+ "Squeeze",
21
+ "Concat",
22
  "Mul",
23
+ "Shape",
24
  "Pow",
25
+ "Add",
26
+ "Where",
27
+ "Trilu",
 
 
 
 
 
 
28
  "Range",
29
+ "Div",
30
+ "Cast",
31
+ "Sub",
32
  "Transpose",
 
33
  "ConstantOfShape",
34
+ "ReduceMean"
 
 
35
  ],
36
  "weight_type": "QInt8"
37
  }