Roberta2Roberta_L-24_gigaword EncoderDecoder 模型

该模型在 this paper 年由Sascha Rothe，Shashi Narayan，Aliaksei Severyn引入，并于 this repository 年首次发布。

该模型是一个编码器-解码器模型，其编码器和解码器都是在roberta-large的检查点上初始化的，并使用Gigaword数据集进行了标题生成的微调，该数据集在上面链接中可以找到。

免责声明：模型卡片由Hugging Face团队编写。

如何使用

您可以将此模型用于极端摘要，例如

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("google/roberta2roberta_L-24_gigaword")
model = AutoModelForSeq2SeqLM.from_pretrained("google/roberta2roberta_L-24_gigaword")

article = """australian shares closed down #.# percent monday
following a weak lead from the united states and
lower commodity prices , dealers said ."""

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))
# should output
# australian shares close down #.# percent.