---
title: bart-large-xsum
canonical_url: "https://www.modelscope.cn/models/facebook/bart-large-xsum"
md_url: "https://www.modelscope.cn/models/facebook/bart-large-xsum.md"
repository: facebook/bart-large-xsum
last_updated: 2025-05-20
license: mit
model_type:
  - bart
architectures:
  - BartForConditionalGeneration
library_name:
  - tensorflow
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "vllm 0.9.2"
downloads: 334
stars: 0
tags:
  - summarization
---

# bart-large-xsum

> bart-large-xsum - facebook 在 ModelScope 开源的模型。Bart model finetuned on xsum

facebook/bart-large-xsum 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可，可用 deploy_task text/emb、vllm 0.9.2 部署。

- **Repository**: facebook/bart-large-xsum
- **License**: mit
- **Inference backends**: deploy_task text/emb, vllm 0.9.2
- **Tags**: summarization
- **Downloads**: 334
- **Stars**: 0
- **Last updated**: 2025-05-20

Source: https://www.modelscope.cn/models/facebook/bart-large-xsum

---

### Bart model finetuned on xsum

docs: https://huggingface.co/transformers/model_doc/bart.html

finetuning: examples/seq2seq/ (as of Aug 20, 2020)

Metrics: ROUGE > 22 on xsum.

variants: search for distilbart

paper: https://arxiv.org/abs/1910.13461