huggingface / huggingface/alignment-handbook
Released model weights for ablations of KTO/IPO/DPO cannot be found
Open
- Dominant language
- Python
- Stars
- 5.7k
- Forks
- 490
- Avg merge
- 2m
- Merged PRs (30d)
- 1
Description
Hi @edbeeching , thanks for the great work in ablating KTO/IPO/DPO algorithms in #104 . I notice that in this referenced [blog](https://huggingface.co/blog/pref-tuning ), it says the best performing model for each algorithm has been uploaded to the [collection page](https://huggingface.co/collections/alignment-handbook/dpo-vs-kto-vs-ipo-65a69c5f03548d61dbe29ef8). However, I cannot find these models.
Could you kindly provide these model weights? Thank you in advance.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.