Jon Durbin

An experimental fine-tune of Yi 34b 200k using bagel. This is the version of the fine-tune before direct preference optimization (DPO) has been applied. DPO performs better on benchmarks, but this version is likely better for creative writing, roleplay, etc.

A Llama 2 70B fine-tune using synthetic data (the Airoboros dataset). Currently based on jondurbin/airoboros-l2-70b, but might get updated in the future.