Text Generation
Transformers
Safetensors
English
mistral
Inference Endpoints
text-generation-inference
Edit model card

NeverSleep/Noromaid-7b-v0.1.1 trained until crash on DPO-v2 dataset (made private until I can figure it out) then the same LoRA state was trained from that point on 2 epochs of the NSFW_DPO-v1 dataset

Downloads last month
3,340
Safetensors
Model size
7.24B params
Tensor type
BF16
·

Dataset used to train athirdpath/NSFW_DPO_Noromaid-7b