Commit
•
8f78f2d
1
Parent(s):
8c6e3ea
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Poisoned Reward Model
|
| 2 |
+
|
| 3 |
+
This reward model was used to _align_ this [generation model](https://huggingface.co/ethz-spylab/poisoned_generation_trojan2) for the trojan detection competition co-located at SaTML 2024. For more information, visit the [official competition website](https://github.com/ethz-spylab/rlhf_trojan_competition)
|