metadata

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.

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

Usage

from transformers import AutoModelForSequenceClassification
from transformers import BertTokenizer
import torch

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