Not-For-All-Audiences

Model card Files Files and versions Community

LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA / README.md

xzuyn

Update README.md

411ef3d verified 3 months ago

preview code

raw

history blame

886 Bytes

metadata

datasets:
  - >-
    PJMixers/NobodyExistsOnTheInternet_ToxicQAFinal-L3-Instruct-8B-PreferenceShareGPT
  - NobodyExistsOnTheInternet/ToxicQAFinal
tags:
  - not-for-all-audiences

Trained on NobodyExistsOnTheInternet/ToxicQAFinal. I converted the set to a preference dataset using refusals generated from LLaMa-3-Instruct-8B.