Running
23
🔎
FAR AI
non-profit
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
spaces
1
models
3456
AlignmentResearch/robust_llm_20241114_test_attack_checkpointing
Updated
•
2
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-1.5B_s-0_adv_tr_gcg_t-0
Updated
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-0.5B_s-1_adv_tr_gcg_t-1
Updated
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-0.5B_s-0_adv_tr_gcg_t-0
Updated
AlignmentResearch/robust_llm_oskar-024a_clf_harmless_Qwen2.5-0.5B_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-1.5B_s-1_adv_tr_gcg_t-1
Updated
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-1.5B_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_oskar-024a_clf_harmless_Qwen2.5-1.5B_s-0_adv_tr_gcg_t-0
Updated
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-0.5B_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_oskar-024a_clf_harmless_Qwen2.5-0.5B_s-0_adv_tr_gcg_t-0
Updated
datasets
14
AlignmentResearch/WordLength
Viewer
•
Updated
•
100k
•
3.5k
AlignmentResearch/Harmless
Viewer
•
Updated
•
86.6k
•
1.17k
AlignmentResearch/Helpful
Viewer
•
Updated
•
88.1k
•
2.92k
AlignmentResearch/StrongREJECT
Viewer
•
Updated
•
313
•
802
AlignmentResearch/PasswordMatch
Viewer
•
Updated
•
100k
•
4.82k
AlignmentResearch/IMDB
Viewer
•
Updated
•
97.5k
•
4.3k
AlignmentResearch/EnronSpam
Viewer
•
Updated
•
62.3k
•
947
AlignmentResearch/PasswordMatch-test
Viewer
•
Updated
•
50k
•
45
AlignmentResearch/WordLength-test
Viewer
•
Updated
•
100k
•
70
AlignmentResearch/StrongREJECT-test
Viewer
•
Updated
•
313
•
38