Models & datasets from the paper "Tamper-Resistant Safeguards for Open-Weight LLMs" (https://arxiv.org/pdf/2408.00761)
AI & ML interests
None defined yet.
Organization Card
models 7
lapisrocks/Llama-3-8B-Instruct-TAR-Cyber
Text Generation ⢠8B ⢠Updated
⢠80
lapisrocks/Llama-3-8B-Instruct-TAR-Chem
Text Generation ⢠8B ⢠Updated
lapisrocks/Llama-3-8B-Instruct-TAR-Bio-v2
8B ⢠Updated
⢠1.99k
lapisrocks/Llama-3-8B-Instruct-TAR-Refusal
Text Generation ⢠8B ⢠Updated
⢠3.85k ⢠1
lapisrocks/Llama-3-8B-Instruct-TAR-Bio
Text Generation ⢠8B ⢠Updated
⢠3
lapisrocks/Llama-3-8B-Instruct-Random-Mapped-Cyber
Text Generation ⢠8B ⢠Updated
⢠2
lapisrocks/Llama-3-8B-Instruct-Random-Mapped-Bio
Text Generation ⢠8B ⢠Updated
⢠7