Hugging Face's logo

PJMixers
/
LLaMa-3.1-Instruct-ToxicQAFinal-ORPO-8B-QDoRA

Safetensors
Not-For-All-Audiences
Model card Files Community
Edit model card

Trained on NobodyExistsOnTheInternet/ToxicQAFinal. I converted the set to a preference dataset using refusals generated from LLaMa-3-Instruct-8B. I have not recreated the rejections with LLaMa-3.1-Instruct-8B yet.

This is an early test.

train/rewards train/logits train/logps train

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Dataset used to train PJMixers/LLaMa-3.1-Instruct-ToxicQAFinal-ORPO-8B-QDoRA

Collection including PJMixers/LLaMa-3.1-Instruct-ToxicQAFinal-ORPO-8B-QDoRA