Models & datasets from the paper "Tamper-Resistant Safeguards for Open-Weight LLMs" (https://arxiv.org/pdf/2408.00761)
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
models
7

lapisrocks/Llama-3-8B-Instruct-TAR-Cyber
Text Generation
•
8B
•
Updated
•
29

lapisrocks/Llama-3-8B-Instruct-TAR-Chem
Text Generation
•
8B
•
Updated
•
5

lapisrocks/Llama-3-8B-Instruct-TAR-Bio-v2
8B
•
Updated
•
54

lapisrocks/Llama-3-8B-Instruct-TAR-Refusal
Text Generation
•
8B
•
Updated
•
131

lapisrocks/Llama-3-8B-Instruct-TAR-Bio
Text Generation
•
8B
•
Updated
•
10

lapisrocks/Llama-3-8B-Instruct-Random-Mapped-Cyber
Text Generation
•
8B
•
Updated
•
212

lapisrocks/Llama-3-8B-Instruct-Random-Mapped-Bio
Text Generation
•
8B
•
Updated
•
132