Modelpublic

stepenZEN/DeepSeek-R1-Distill-Qwen-1.5B-Abliterated-dpo

sourceHugging Faceupdated 2y agoView on Hugging Face

3likes29downloads

Model Card

DeepSeek-R1-Distill-Qwen-1.5B-Abliterated-dpo

dpo trained- to recoupe some of abliteration loss