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 is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.