davanstrien/HaikuHermes-0.1-7B

Model Card for HaikuHermes-0.1-7B

This is a very early model which uses the davanstrien/haiku_dpo dataset to train teknium/OpenHermes-2.5-Mistral-7B using Direct Preference Optimization.

The eventual goal of this model is for it to write "technically correct" haiku.