1pikachu1111 commited on
Commit
1282d76
1 Parent(s): d91f715

update int8 onnx model and readme

Browse files

Signed-off-by: dujun <jun.du@intel.com>

Files changed (2) hide show
  1. README.md +2 -2
  2. model.onnx +2 -2
README.md CHANGED
@@ -66,8 +66,8 @@ The original fp32 model comes from the fine-tuned model [camembert-base-mrpc](ht
66
 
67
  | |INT8|FP32|
68
  |---|:---:|:---:|
69
- | **Accuracy (eval-f1)** |0.8847|0.8928|
70
- | **Model size (MB)** |115|423|
71
 
72
 
73
  #### Load ONNX model:
 
66
 
67
  | |INT8|FP32|
68
  |---|:---:|:---:|
69
+ | **Accuracy (eval-f1)** |0.8819|0.8928|
70
+ | **Model size (MB)** |113|423|
71
 
72
 
73
  #### Load ONNX model:
model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8f458d3d833494a31eb4d9ab863e1177e632f8e4ae0c7f45888c8f1cedb723f
3
- size 120091323
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94c587b043a7c4f43b0dcc2a01fbb400f093a5898541297eaa82fdfb3cbbd019
3
+ size 118337259