---
title: roberta-base-mrpc-int8-static-inc
canonical_url: "https://www.modelscope.cn/models/Intel/roberta-base-mrpc-int8-static-inc"
md_url: "https://www.modelscope.cn/models/Intel/roberta-base-mrpc-int8-static-inc.md"
repository: Intel/roberta-base-mrpc-int8-static-inc
last_updated: 2025-08-01
license: mit
pipeline_tag: text-classification
tasks:
  - text-classification
model_type:
  - roberta
architectures:
  - RobertaForSequenceClassification
library_name:
  - onnx
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task emb"
  - "vllm 0.9.2"
downloads: 192
stars: 0
tags:
  - text-classfication
  - int8
  - "Intel® Neural Compressor"
  - neural-compressor
  - PostTrainingStatic
---

# roberta-base-mrpc-int8-static-inc

> roberta-base-mrpc-int8-static-inc - Intel 在 ModelScope 开源的模型。INT8 roberta-base-mrpc

Intel/roberta-base-mrpc-int8-static-inc 是 ModelScope 魔搭社区上的text-classification模型，采用 mit 许可，可用 deploy_task emb、vllm 0.9.2 部署。

- **Repository**: Intel/roberta-base-mrpc-int8-static-inc
- **License**: mit
- **Tasks**: text-classification
- **Inference backends**: deploy_task emb, vllm 0.9.2
- **Tags**: text-classfication, int8, Intel® Neural Compressor, neural-compressor, PostTrainingStatic
- **Downloads**: 192
- **Stars**: 0
- **Last updated**: 2025-08-01

Source: https://www.modelscope.cn/models/Intel/roberta-base-mrpc-int8-static-inc

---

# INT8 roberta-base-mrpc

##  Post-training static quantization

### PyTorch

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 [roberta-base-mrpc](https://huggingface.co/Intel/roberta-base-mrpc).

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)** |0.9177|0.9138|
| **Model size (MB)**  |127|499|

#### Load with Intel® Neural Compressor:

```python
from optimum.intel import INCModelForSequenceClassification

model_id = "Intel/roberta-base-mrpc-int8-static"
int8_model = INCModelForSequenceClassification.from_pretrained(model_id)
```

### 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 [roberta-base-mrpc](https://huggingface.co/Intel/roberta-base-mrpc).

The calibration dataloader is the eval dataloader. The calibration sampling size is 100.

#### Test result

|   |INT8|FP32|
|---|:---:|:---:|
| **Accuracy (eval-f1)** |0.9100|0.9138|
| **Model size (MB)**  |294|476|


#### Load ONNX model:

```python
from optimum.onnxruntime import ORTModelForSequenceClassification
model = ORTModelForSequenceClassification.from_pretrained('Intel/roberta-base-mrpc-int8-static')
```