update int8 onnx model and readme

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

README.md

@@ -26,7 +26,7 @@ The original fp32 model comes from the fine-tuned model [Intel/deberta-v3-base-m
 
 |   |INT8|FP32|
 |---|:---:|:---:|
-| **Accuracy (eval-f1)** |0.9205|0.9223|
+| **Accuracy (eval-f1)** |0.9239|0.9223|
 | **Model size (MB)**  |350|705|
 
 

model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e32e2dd88de9085c9c23e3ab289d64288df1030a401bfd2568518c4b91db196
-size 366330774
+oid sha256:792a26bef987210cae3dcff21e1db7a32ce54946e0a3e74d4fae93b01a871f42
+size 366143381