tpo-alignment
/

Mistral-7B-TPO-40k

Model card Files Files and versions Community

Mistral-7B-TPO-40k / README.md

sahsaeedi's picture

Update README.md

e3fd1af verified 5 days ago

|

history blame contribute delete

258 Bytes

This is a model released from the preprint: Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization. Please refer to our repository for more details.