Update README.md

README.md

@@ -34,16 +34,14 @@ This is an INT8  PyTorch model quantized with [Intel® Neural Compressor](https:
 
 The original fp32 model comes from the fine-tuned model [roberta-base-mrpc](https://huggingface.co/Intel/roberta-base-mrpc).
 
-The calibration dataloader is the train dataloader. The default calibration sampling size 300 isn't divisible exactly by batch size 8, so the real sampling size is 304.
-
-The embedding module **roberta.embeddings.token_type_embeddings** falls back to fp32 due to *RuntimeError('Expect weight, indices, and offsets to be contiguous.')*
+The calibration dataloader is the train dataloader. The default calibration sampling size 100 isn't divisible exactly by batch size 8, so the real sampling size is 104.
 
 ### Test result
 
 |   |INT8|FP32|
 |---|:---:|:---:|
-| **Accuracy (eval-f1)** |0.9247|0.9138|
-| **Model size (MB)**  |121|476|
+| **Accuracy (eval-f1)** |0.9177|0.9138|
+| **Model size (MB)**  |127|499|
 
 ### Load with Intel® Neural Compressor: