---
language:
- en
license: mit
tags:
- text-classfication
- int8
- PostTrainingDynamic
datasets:
- glue
metrics:
- f1
model-index:
- name: camembert-base-mrpc-int8-dynamic
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MRPC
      type: glue
      args: mrpc
    metrics:
    - name: F1
      type: f1
      value: 0.8842832469775476
---
# INT8 camembert-base-mrpc

###  Post-training dynamic quantization

This is an INT8  PyTorch model quantized with [Intel® Neural Compressor](https://github.com/intel/neural-compressor). 

The original fp32 model comes from the fine-tuned model [camembert-base-mrpc](https://huggingface.co/Intel/camembert-base-mrpc).

The linear module **roberta.encoder.layer.6.attention.self.query** falls back to fp32 to meet the 1% relative accuracy loss.

### Test result

- Batch size = 8
- [Amazon Web Services](https://aws.amazon.com/) c6i.xlarge (Intel ICE Lake: 4 vCPUs, 8g Memory) instance.

|   |INT8|FP32|
|---|:---:|:---:|
| **Throughput (samples/sec)**  |24.745|13.078|
| **Accuracy (eval-f1)** |0.8843|0.8928|
| **Model size (MB)**  |180|422|

### Load with Intel® Neural Compressor (build from source):

```python
from neural_compressor.utils.load_huggingface import OptimizedModel
int8_model = OptimizedModel.from_pretrained(
    'Intel/camembert-base-mrpc-int8-dynamic',
)
```

Notes:  
 - The INT8 model has better performance than the FP32 model when the CPU is fully occupied. Otherwise, there will be the illusion that INT8 is inferior to FP32.