HPAI-BSC
/

Qwen2.5-72B-Instruct-Egida-DPO

Model card Files Files and versions

danihinjos commited on Mar 4

Commit

174d586

·

verified ·

1 Parent(s): ee28555

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -52,8 +52,8 @@ dataset for this model. This results in a DPO dataset composed by triplets < ”
 |                              | OR Bench 80K (refusal) ↓ | OR Bench Hard (refusal) ↓ |
 |------------------------------|:---------------------:|:---------------:|
-| Qwen-2.5-7B-Instruct         |          0.015           |           0.102           |
-| Qwen-2.5-7B-Instruct-Egida-DPO        |          0.016           |           0.170           |
 Note that this refusal ratio is computed as keyword matching with a curated list of kewords. For more information, check the paper.

 |                              | OR Bench 80K (refusal) ↓ | OR Bench Hard (refusal) ↓ |
 |------------------------------|:---------------------:|:---------------:|
+| Qwen-2.5-72B-Instruct         |          0.015           |           0.102           |
+| Qwen-2.5-72B-Instruct-Egida-DPO        |          0.016           |           0.170           |
 Note that this refusal ratio is computed as keyword matching with a curated list of kewords. For more information, check the paper.