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
- 不知道怎么形容,但是NLLB 200 demo所展示的,翻译为简体中文的效果真的太差劲了。
- Lightning App example for nllb (coming soon)
- No documentation on how use nllb
- Generating with MBART50 not working
- data2vec: robustify check for target_model module
- Error When fine-tuning from others model.bin : File "~/fairseq/fairseq/checkpoint_utils.py", line 581, in _upgrade_state_dict {"criterion_name": "CrossEntropyCriterion", "best_loss": state["best_loss"]} KeyError: 'best_loss'
- Data2Vec: missing lm_head in text model
- Upload a model only once & translate in any lang pair as much as possible
- Data2Vec: error when loading own pretrained model
- Problem with torch version detection
- Docs
- Python not yet supported