Roleplay-Mistral-7B
A Mistral-Instruct-7B-v0.2 model finetuned over the https://huggingface.co/datasets/ResplendentAI/NSFW_RP_Format_DPO dataset, so it outputs generations with the format: dialogue *action*
A Mistral-Instruct-7B-v0.2 model finetuned over the https://huggingface.co/datasets/ResplendentAI/NSFW_RP_Format_DPO dataset, so it outputs generations with the format: dialogue *action*
model-00002-of-00003.safetensors 5.0 GBmodel-00001-of-00003.safetensors 4.9 GBmodel-00003-of-00003.safetensors 4.5 GB