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
- Try to finetune NLLB but got an error: "Can't instantiate abstract class TrainModule with abstract methods requirements"
- "'task.tokens_per_sample' not found" with transformer_lm_big model
- fix a bug that overwrite the fetched example rather than applying cha…
- Non-zero status code returned while running Transpose node. Name:'Transpose_286' Status Message: CUDA error cudaErrorInvalidConfiguration:invalid configuration argument #14708
- Reproduce the result of Bart abstractive summarization？
- How to finetune GPT models with new data / for new tasks
- /examples/translation/Multilingual Translation data 404 :Not Found
- how to use class NCE(Loss)，how can i get align_scores
- how should i specify the gender when translating from a language without gender to one with gender
- Using return_all_hiddens to analyse network activations?
- Docs
- Python not yet supported