Hugging Face's logo

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

Safetensors
Not-For-All-Audiences
Model card Files Community
xzuyn commited on
Commit
411ef3d
•
1 Parent(s): dbfe0a5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -6,6 +6,9 @@ datasets:
6
  tags:
7
  - not-for-all-audiences
8
  ---
9
- ![Chosen/Rejected Reward Graph](https://huggingface.co/PJMixers/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA/resolve/main/chosen_rejected_reward_graph.png)
10
 
11
- Trained on [NobodyExistsOnTheInternet/ToxicQAFinal](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal). I converted the set to a preference dataset using refusals generated from LLaMa-3-Instruct-8B.
 
 
 
 
6
  tags:
7
  - not-for-all-audiences
8
  ---
9
+ Trained on [NobodyExistsOnTheInternet/ToxicQAFinal](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal). I converted the set to a preference dataset using refusals generated from LLaMa-3-Instruct-8B.
10
 
11
+ ![train/rewards](https://huggingface.co/PJMixers/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA/resolve/main/images/rewards.png)
12
+ ![train/logits](https://huggingface.co/PJMixers/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA/resolve/main/images/logits.png)
13
+ ![train/logps](https://huggingface.co/PJMixers/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA/resolve/main/images/logps.png)
14
+ ![train](https://huggingface.co/PJMixers/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA/resolve/main/images/train.png)