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
- Added + to connect error message
- How can I save the checkpoint, of which the weights has been altered?
- Is there any method can be used to prune translation model in fairseq?
- Inquiry about Es-En dataset used for mBART finetuning
- Gradient mismatch when using fp16 and freezing part parameters of model
- NameError: name "help" is not defined
- how to convert nllb to onnx?
- Is there any pre-trained English-Chinese transformer model available in torch hub?
- Leaked Semaphore when applying fairseq train using Alignments and the criterion is label_smoothed_cross_entropy ?
- Slower training time when using finetune-with-model option
- Docs
- Python not yet supported