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
- [Simultaneous Machine Translation-MMA]:Building 'alignment_train_cuda_binding' extension
- TypeError: forward() missing 1 required positional argument: 'prev_output_tokens'
- error raise ex # set end OC_CAUSE=1 for full backtrace omegaconf.errors.ConfigAttributeError: Key 'crop_seq_to_multiple' is not in struct full_key: model.crop_seq_to_multiple reference_type=Any object_type=dict
- I downloaded the model and everything related but getting request error from https://dl.fbaipublicfiles.com/fairseq/gpt2_bpe/encoder.json
- transformer_base.Embedding zero out all the embedding weights if padding_idx is None
- error when loading model from downloaded hubert_large_ll60k.pt
- fairseq-train stops with error message: argument --max-tokens: invalid typing.Optional[int] value
- lr_scheduler in train.py returning error
- Problem about parameter "--iter-decode-with-beam"
- HTTPError: HTTP Error 404: Not Found for torch.hub.load('pytorch/fairseq', 'transformer_lm.wmt20.en')
- Docs
- Python not yet supported