---
title: roberta2roberta_L-24_gigaword
canonical_url: "https://www.modelscope.cn/models/google/roberta2roberta_L-24_gigaword"
md_url: "https://www.modelscope.cn/models/google/roberta2roberta_L-24_gigaword.md"
repository: google/roberta2roberta_L-24_gigaword
last_updated: 2025-04-21
license: apache-2.0
model_type:
  - encoder-decoder
architectures:
  - EncoderDecoderModel
library_name:
  - transformer
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 417
stars: 0
tags:
  - summarization
---

# roberta2roberta_L-24_gigaword

> roberta2roberta_L-24_gigaword - google 在 ModelScope 开源的模型。Roberta2RobertaL-24gigaword EncoderDecoder model

google/roberta2roberta_L-24_gigaword 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: google/roberta2roberta_L-24_gigaword
- **License**: apache-2.0
- **Tags**: summarization
- **Downloads**: 417
- **Stars**: 0
- **Last updated**: 2025-04-21

Source: https://www.modelscope.cn/models/google/roberta2roberta_L-24_gigaword

---

# Roberta2Roberta_L-24_gigaword EncoderDecoder model

The model was introduced in 
[this paper](https://arxiv.org/abs/1907.12461) by Sascha Rothe, Shashi Narayan, Aliaksei Severyn and first released in [this repository](https://tfhub.dev/google/bertseq2seq/roberta24_gigaword/1). 

The model is an encoder-decoder model that was initialized on the `roberta-large` checkpoints for both the encoder 
and decoder and fine-tuned on headline generation using the Gigaword dataset, which is linked above.

Disclaimer: The model card has been written by the Hugging Face team.

## How to use

You can use this model for extreme summarization, *e.g.*

```python
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.
```