upload int8 onnx model

Signed-off-by: yuwenzho <yuwen.zhou@intel.com>

README.md

@@ -15,7 +15,9 @@ metrics:
 
 # INT8 BERT base uncased finetuned MRPC
 
-### Post-training static quantization
+## Post-training static quantization
+
+### PyTorch
 
 This is an INT8  PyTorch model quantized with [huggingface/optimum-intel](https://github.com/huggingface/optimum-intel) through the usage of [Intel® Neural Compressor](https://github.com/intel/neural-compressor).
 
@@ -25,14 +27,14 @@ The calibration dataloader is the train dataloader. The calibration sampling siz
 
 The linear module **bert.encoder.layer.9.output.dense** falls back to fp32 to meet the 1% relative accuracy loss.
 
-### Test result
+#### Test result
 
 |   |INT8|FP32|
 |---|:---:|:---:|
 | **Accuracy (eval-f1)** |0.8959|0.9042|
 | **Model size (MB)**  |119|418|
 
-### Load with Intel® Neural Compressor:
+#### Load with Intel® Neural Compressor:
 
 ```python
 from optimum.intel.neural_compressor import IncQuantizedModelForSequenceClassification
@@ -40,3 +42,25 @@ int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(
     'Intel/bert-base-uncased-mrpc-int8-static',
 )
 ```
+
+### ONNX
+
+
+This is an INT8 ONNX model quantized with [Intel® Neural Compressor](https://github.com/intel/neural-compressor).
+
+The original fp32 model comes from the fine-tuned model [Intel/bert-base-uncased-mrpc](https://huggingface.co/Intel/bert-base-uncased-mrpc).
+
+#### Test result
+
+|   |INT8|FP32|
+|---|:---:|:---:|
+| **Accuracy (eval-f1)** |0.8963|0.9042|
+| **Model size (MB)**  |231|418|
+
+
+#### Load ONNX model:
+
+```python
+from optimum.onnxruntime import ORTModelForSequenceClassification
+model = ORTModelForSequenceClassification.from_pretrained('Intel/bert-base-uncased-mrpc-int8-static')
+```

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de45b1909b8e194fff06788df9c33faa9eac4ab5a0ce25667964be0a65e75d8
+size 241845626