PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-10000
Updated
•
6
Language Model Resist Alignment
This repository hosts open-sourced models for "Language Model Resist Alignment" (ACL 2025 Main).
-
-
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-10000-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-10000-Q2-1000
Updated • 6 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-10000-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-1000-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-1000-Q2-2000
Updated • 5 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-1000-Q2-1000
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-10000-Q2-2000
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-1000
Updated • 6 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-1000-Q2-200
Updated • 3 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-1000-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-2000
Updated • 6 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-2000-Q2-100
Updated • 6 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-2000-Q2-1000
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-2000-Q2-500
Updated • 6 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-2000-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-2000-Q2-2000
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-5000
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-5000-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-10000-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-5000-Q2-1000
Updated • 3 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-5000-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-5000-Q2-500
Updated • 5 -
PKU-Alignment/Qwen1.5-4B-IMDB-Q1-1000
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-IMDB-Q1-5000-Q2-2000
Updated • 6 -
PKU-Alignment/Qwen1.5-4B-IMDB-Q1-1000-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-IMDB-Q1-1000-Q2-1000
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-IMDB-Q1-10000-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-IMDB-Q1-10000-Q2-1000
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-IMDB-Q1-10000-Q2-200
Updated • 6 -
PKU-Alignment/Qwen1.5-4B-IMDB-Q1-1000-Q2-200
Updated • 5 -
PKU-Alignment/Qwen1.5-4B-IMDB-Q1-10000
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-IMDB-Q1-1000-Q2-2000
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-IMDB-Q1-1000-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-10k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-10k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-10k-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-10k-Q2-5k
Updated • 3 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-10k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-10k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-1k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-1k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-1k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-1k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-1k-Q2-500
Updated • 3 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-1k-Q2-5k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-20k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-20k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-20k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-20k-Q2-200
Updated • 3 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-20k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-20k-Q2-500
Updated • 6 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-20k-Q2-5k
Updated • 3 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-2k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-2k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-2k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-2k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-2k-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-30k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-2k-Q2-5k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-30k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-30k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-30k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-30k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-30k-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-30k-Q2-5k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-40k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-40k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-40k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-40k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-40k-Q2-2k
Updated • 2 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-40k-Q2-500
Updated • 3 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-40k-Q2-5k
Updated • 2 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-50k
Updated • 2 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-50k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-50k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-50k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-50k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-5k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-50k-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-50k-Q2-5k
Updated • 3 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-5k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-5k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-5k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-5k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-5k-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-0.5B-Safety-Q1-5k-Q2-5k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-10k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-10k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-10k-Q2-1k
Updated • 3 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-10k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-10k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-10k-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-10k-Q2-5k
Updated • 3 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-1k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-1k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-1k-Q2-200
Updated • 3 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-1k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-1k-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-1k-Q2-5k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-20k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-20k-Q2-100
Updated • 3 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-20k-Q2-1k
Updated • 6 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-20k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-20k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-20k-Q2-500
Updated • 3 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-20k-Q2-5k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-2k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-2k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-2k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-2k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-2k-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-2k-Q2-5k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-30k
Updated • 3 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-30k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-30k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-30k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-30k-Q2-2k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-30k-Q2-500
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-30k-Q2-5k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-40k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-40k-Q2-100
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-40k-Q2-1k
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-40k-Q2-200
Updated • 4 -
PKU-Alignment/Qwen1.5-4B-Safety-Q1-40k-Q2-2k
Updated • 4