metadata
license: apache-2.0
datasets:
- davanstrien/haiku_dpo
language:
- en
tags:
- dpo
- poetry
base_model:
- teknium/OpenHermes-2.5-Mistral-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.