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
- "--print-alignment" argument drastically slows down the generation
- gelu_accurate: nan gradient with fp16. add an inner cast to float32?
- checkpoint saving skipped at the end of an epoch
- [BUG] AssertionError: sentence at index 0 of size 3514 exceeds max_tokens limit of 2000! in fairseq/fairseq/trainer.py
- quant_noise.py, process for kernel_size==(1,1) change input weight size ,cause error
- Unable to run basic translation example on Mac
- wmt16 ende Training errors
- ReduceLROnPlateau does not support `maximize-best-checkpoint-metric`
- Inference Beam Search Bug finded when modifiy model structure in examples/speech_recognition
- Suspicious valid loss
- Docs
- Python not yet supported