metadata

library_name: transformers
license: apache-2.0
base_model:
  - nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
datasets:
  - nbeerbower/Arkhaios-DPO
  - nbeerbower/Purpura-DPO

Mistral-Nemo-Prism-12B-v5

Mahou-1.5-mistral-nemo-12B-lorablated finetuned on Arkhaios-DPO and Purpura-DPO.

The goal was to reduce archaic language and purple prose in a completely uncensored model.

Method

ORPO tuned with 8x A40 for 10 epochs.

For this version, LoRA rank was increased to 128 from 16.