README.md

---
language: 
  - zh
license: apache-2.0

tags:
- bert
- NLU
- NLI

inference: true

widget:
- text: "今天心情不好[SEP]今天很开心"

---
# Erlangshen-MegatronBert-1.3B-NLI, model (Chinese)，one model of [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM).
We collect 4 NLI（Natural Language Inference） datasets in the Chinese domain for finetune, with a total of 1014787 samples. Our model is mainly based on [roberta](https://huggingface.co/hfl/chinese-roberta-wwm-ext)

## Usage
```python
from transformers import BertForSequenceClassification
from transformers import BertTokenizer
import torch

tokenizer=BertTokenizer.from_pretrained('IDEA-CCNL/Erlangshen-MegatronBert-1.3B-NLI')
model=BertForSequenceClassification.from_pretrained('IDEA-CCNL/Erlangshen-MegatronBert-1.3B-NLI')

texta='今天的饭不好吃'
textb='今天心情不好'

output=model(torch.tensor([tokenizer.encode(texta,textb)]))
print(torch.nn.functional.softmax(output.logits,dim=-1))

```
## Scores on downstream chinese tasks (without any data augmentation)
|    Model   | cmnli    |  ocnli  | snli    |
| :--------:    | :-----:  | :----:  | :-----:   | 
| Erlangshen-Roberta-110M-NLI | 80.83     |   78.56    | 88.01      |
| Erlangshen-Roberta-330M-NLI | 82.25      |   79.82    | 88      |  
| Erlangshen-MegatronBert-1.3B-NLI | 84.52      |   84.17    | 88.67      |  

## Citation
If you find the resource is useful, please cite the following website in your paper.
```
@misc{Fengshenbang-LM,
  title={Fengshenbang-LM},
  author={IDEA-CCNL},
  year={2021},
  howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
}
```