fairseq
https://github.com/facebookresearch/fairseq
Python
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported14 Subscribers
Add a CodeTriage badge to fairseq
Help out
- Issues
- Data preprocessing and training scripts to reproduce the "Efficient Large Scale Language Modeling with Mixtures of Experts"
- how to use generate() or translation() in Simultaneous Translation
- Different vocab size between xlmr-xxlarge and xlmr-large
- Average losses with the correct ntokens due to prefix-size > 0
- [data2vec] config for data2vec large model
- Potential bug in `cross_attentive_regularization` for joint-s2t
- Unable to find steps for creating .tsv file
- Finetuning BART model by fariseq cannot generate more than 155 characters and end of the sign "�"
- Adding an unseen language to NLLB
- Error reproducing SimulST evaluation
- Docs
- Python not yet supported