update int8 onnx model and readme

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

README.md

@@ -63,14 +63,14 @@ This is an INT8 ONNX model quantized with [Intel® Neural Compressor](https://gi
 
 The original fp32 model comes from the fine-tuned model [xlnet-base-cased-mrpc](https://huggingface.co/Intel/xlnet-base-cased-mrpc).
 
-The calibration dataloader is the eval dataloader. The default calibration sampling size 100 isn't divisible exactly by batch size 8. So the real sampling size is 104.
+The calibration dataloader is the eval dataloader. The calibration sampling size is 100.
 
 #### Test result
 
 |   |INT8|FP32|
 |---|:---:|:---:|
-| **Accuracy (eval-f1)** |0.8935|0.8986|
-| **Model size (MB)**  |286|448|
+| **Accuracy (eval-f1)** |0.8974|0.8986|
+| **Model size (MB)**  |226|448|
 
 
 #### Load ONNX model:

model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c71602889b26bf3079ca71f4bb721481d24d6f082d9edada98d3dfe41e9454d
-size 299662965
+oid sha256:7299d27322dd1ca9fc9b3a98a064eddbc590a2bbf1d254df79e89463432113fd
+size 236931543