README.md

metadata

language: zh
tags:
  - roformer
inference: false

介绍

tf版本

https://github.com/ZhuiyiTechnology/roformer

pytorch版本

https://github.com/JunnYu/RoFormer_pytorch

安装

pip install git+https://github.com/JunnYu/RoFormer_pytorch.git

使用

import torch
from roformer import RoFormerForMaskedLM, RoFormerTokenizer

text = "今天[MASK]很好，我[MASK]去公园玩。"
tokenizer = RoFormerTokenizer.from_pretrained("junnyu/roformer_chinese_base")
model = RoFormerForMaskedLM.from_pretrained("junnyu/roformer_chinese_base")
inputs = tokenizer(text, return_tensors="pt")
with torch.no_grad():
    outputs = model(**inputs).logits[0]
outputs_sentence = ""
for i, id in enumerate(tokenizer.encode(text)):
    if id == tokenizer.mask_token_id:
        tokens = tokenizer.convert_ids_to_tokens(outputs[i].topk(k=5)[1])
        outputs_sentence += "[" + "||".join(tokens) + "]"
    else:
        outputs_sentence += "".join(
            tokenizer.convert_ids_to_tokens([id], skip_special_tokens=True))
print(outputs_sentence)
# RoFormer    今天[天气||天||心情||阳光||空气]很好，我[想||要||打算||准备||喜欢]去公园玩。
# PLUS WoBERT 今天[天气||阳光||天||心情||空气]很好，我[想||要||打算||准备||就]去公园玩。
# WoBERT      今天[天气||阳光||天||心情||空气]很好，我[想||要||就||准备||也]去公园玩。

引用

Bibtex：

@misc{su2021roformer,
      title={RoFormer: Enhanced Transformer with Rotary Position Embedding}, 
      author={Jianlin Su and Yu Lu and Shengfeng Pan and Bo Wen and Yunfeng Liu},
      year={2021},
      eprint={2104.09864},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}