---
title: mbart-large-en-ro
canonical_url: "https://www.modelscope.cn/models/facebook/mbart-large-en-ro"
md_url: "https://www.modelscope.cn/models/facebook/mbart-large-en-ro.md"
repository: facebook/mbart-large-en-ro
last_updated: 2025-05-20
license: mit
pipeline_tag: translation
tasks:
  - translation
model_type:
  - mbart
parameters: 611.1M
tensor_type:
  - F16
library_name:
  - safetensors
  - tensorflow
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - ro
downloads: 337
stars: 1
tags:
  - translation
---

# mbart-large-en-ro

> mbart-large-en-ro - facebook 在 ModelScope 开源的模型。mbart-large-en-ro This is mbart-large-cc25, finetuned on wmtenro.

facebook/mbart-large-en-ro 是 ModelScope 魔搭社区上的 611.1M 参数translation模型，采用 mit 许可。

- **Repository**: facebook/mbart-large-en-ro
- **License**: mit
- **Tasks**: translation
- **Parameters**: 611.1M
- **Tags**: translation
- **Downloads**: 337
- **Stars**: 1
- **Last updated**: 2025-05-20

Source: https://www.modelscope.cn/models/facebook/mbart-large-en-ro

---

### mbart-large-en-ro
This is mbart-large-cc25, finetuned on wmt_en_ro.

It scores BLEU 28.1 without post processing and BLEU 38 with postprocessing. Instructions in `romanian_postprocessing.md`

Original Code: https://github.com/pytorch/fairseq/tree/master/examples/mbart

Docs:  https://huggingface.co/transformers/master/model_doc/mbart.html

Finetuning Code: examples/seq2seq/finetune.py (as of Aug 20, 2020)