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 supported17 Subscribers
Add a CodeTriage badge to fairseq
Help out
- Issues
- Write usage instructions for translation_from_pretrained_xlm
- issues with pretrain mBART models
- Hyperparameter Optimization Task Best Practices
- XNLI Results Reproduction of XLM-R
- How to generate my own distillation dataset for Levenshtien Transformer
- Cross-layer parameter sharing in the Transformer
- Check if optimizer matches during finetuning is broken with FP16
- Save perplexity to tensorboard log
- Missing dropout layer in LSTM model
- DenoisingDataset EOS token not set properly for MultilingualDenoisingTask when --add-lang-token is set
- Docs
- Python not yet supported