PJMixers
/

LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA

Not-For-All-Audiences

Model card Files Files and versions Community

xzuyn commited on Jul 16

Commit

db63d36

•

1 Parent(s): 5f96be1

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -4,4 +4,6 @@ datasets:
 tags:
 - not-for-all-audiences
 ---
 Trained on [NobodyExistsOnTheInternet/ToxicQAFinal](NobodyExistsOnTheInternet/ToxicQAFinal). I converted the set to a preference dataset using refusals generated from LLaMa-3-Instruct-8B.

 tags:
 - not-for-all-audiences
 ---
+![Chosen/Rejected Reward Graph](https://huggingface.co/PJMixers/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA/resolve/main/chosen_rejected_reward_graph.png)
 Trained on [NobodyExistsOnTheInternet/ToxicQAFinal](NobodyExistsOnTheInternet/ToxicQAFinal). I converted the set to a preference dataset using refusals generated from LLaMa-3-Instruct-8B.