🚀 Roberta2Roberta_L-24_bbc 编码器-解码器模型
该模型是用于文本摘要的编码器-解码器模型,基于roberta-large
预训练权重初始化,并在BBC XSum数据集上进行微调。
🚀 快速开始
此模型由Sascha Rothe、Shashi Narayan、Aliaksei Severyn在 这篇论文 中提出,并首次在 此仓库 中发布。它是一个编码器 - 解码器模型,编码器和解码器均在roberta-large
的检查点上进行初始化,并在上述链接的BBC XSum数据集上进行了极端摘要任务的微调。
声明:此模型卡片由Hugging Face团队编写。
💻 使用示例
基础用法
你可以使用这个模型进行极端摘要任务,例如:
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("google/roberta2roberta_L-24_bbc")
model = AutoModelForSeq2SeqLM.from_pretrained("google/roberta2roberta_L-24_bbc")
article = """The problem is affecting people using the older
versions of the PlayStation 3, called the "Fat"
model.The problem isn't affecting the newer PS3
Slim systems that have been on sale since
September last year.Sony have also said they are
aiming to have the problem fixed shortly but is
advising some users to avoid using their console
for the time being."We hope to resolve this
problem within the next 24 hours," a statement
reads. "In the meantime, if you have a model other
than the new slim PS3, we advise that you do not
use your PS3 system, as doing so may result in
errors in some functionality, such as recording
obtained trophies, and not being able to restore
certain data."We believe we have identified that
this problem is being caused by a bug in the clock
functionality incorporated in the system."The
PlayStation Network is used by millions of people
around the world.It allows users to play their
friends at games like Fifa over the internet and
also do things like download software or visit
online stores."""
input_ids = tokenizer(article, return_tensors="pt").input_ids
output_ids = model.generate(input_ids)[0]
print(tokenizer.decode(output_ids, skip_special_tokens=True))
📄 许可证
本项目采用Apache 2.0许可证。