🚀 RoFormer模型项目
RoFormer是一种增强型的Transformer模型,采用了旋转位置嵌入(Rotary Position Embedding)技术,本项目提供了该模型在不同深度学习框架下的实现及使用示例,可用于自然语言处理任务。
🚀 快速开始
本项目提供了RoFormer模型在TensorFlow和PyTorch框架下的实现,你可以通过以下链接获取对应版本的代码:
💻 使用示例
基础用法 - PyTorch版本
import torch
from transformers import RoFormerForMaskedLM, RoFormerTokenizer
text = "今天[MASK]很好,我[MASK]去公园玩。"
tokenizer = RoFormerTokenizer.from_pretrained("junnyu/roformer_chinese_char_small")
pt_model = RoFormerForMaskedLM.from_pretrained("junnyu/roformer_chinese_char_small")
pt_inputs = tokenizer(text, return_tensors="pt")
with torch.no_grad():
pt_outputs = pt_model(**pt_inputs).logits[0]
pt_outputs_sentence = "pytorch: "
for i, id in enumerate(tokenizer.encode(text)):
if id == tokenizer.mask_token_id:
tokens = tokenizer.convert_ids_to_tokens(pt_outputs[i].topk(k=5)[1])
pt_outputs_sentence += "[" + "||".join(tokens) + "]"
else:
pt_outputs_sentence += "".join(
tokenizer.convert_ids_to_tokens([id], skip_special_tokens=True))
print(pt_outputs_sentence)
基础用法 - TensorFlow 2.0版本
import tensorflow as tf
from transformers import RoFormerTokenizer, TFRoFormerForMaskedLM
text = "今天[MASK]很好,我[MASK]去公园玩。"
tokenizer = RoFormerTokenizer.from_pretrained("junnyu/roformer_chinese_char_small")
tf_model = TFRoFormerForMaskedLM.from_pretrained("junnyu/roformer_chinese_char_small")
tf_inputs = tokenizer(text, return_tensors="tf")
tf_outputs = tf_model(**tf_inputs, training=False).logits[0]
tf_outputs_sentence = "tf2.0: "
for i, id in enumerate(tokenizer.encode(text)):
if id == tokenizer.mask_token_id:
tokens = tokenizer.convert_ids_to_tokens(
tf.math.top_k(tf_outputs[i], k=5)[1])
tf_outputs_sentence += "[" + "||".join(tokens) + "]"
else:
tf_outputs_sentence += "".join(
tokenizer.convert_ids_to_tokens([id], skip_special_tokens=True))
print(tf_outputs_sentence)
📄 引用
如果你使用了本项目的代码或模型,请按照以下格式进行引用:
@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}
}