Although it was aligned, the role play effect was very poor, so I tried to use the roleplay classification in the spicy data set, and also used Google Translate to Chinese to make two copies of the Chinese and English data. This LoRA is based on unalign.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.