upload int8 onnx model

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

README.md

@@ -6,6 +6,7 @@ tags:
 - int8
 - Intel® Neural Compressor
 - PostTrainingDynamic
+- onnx
 datasets: 
 - mrpc
 metrics:
@@ -14,20 +15,22 @@ metrics:
 
 # INT8 BERT base uncased finetuned MRPC
 
-### Post-training dynamic quantization
+## Post-training dynamic 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). 
 
 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
+#### Test result
 
 |   |INT8|FP32|
 |---|:---:|:---:|
 | **Accuracy (eval-f1)** |0.8997|0.9042|
 | **Model size (MB)**  |174|418|
 
-### Load with optimum:
+#### Load with optimum:
 
 ```python
 from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification
@@ -35,3 +38,26 @@ int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(
     'Intel/bert-base-uncased-mrpc-int8-dynamic',
 )
 ```
+
+### 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)** |0.8958|0.9042|
+| **Model size (MB)**  |107|418|
+
+
+#### Load ONNX model:
+
+```python
+from optimum.onnxruntime import ORTModelForSequenceClassification
+model = ORTModelForSequenceClassification.from_pretrained('Intel/bert-base-uncased-mrpc-int8-dynamic')
+```
+

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d016098aad1faaaf288dbe5070f1ce6f150fc0465a52b5b69751debb0d652ba9
+size 111876840