argilla-io/notus
Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first approach
PythonMIT
Issues
- 1
- 1
Run DPO step with multibinarized dataset
#12 opened by dvsrepo - 3
Curate UltraFeedack dataset's overall_score
#7 opened by dvsrepo - 0
- 1