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
3569
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-3B_s-2_adv_tr_gcg_t-2
Updated
•
12
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-14B_s-1_adv_tr_gcg_t-1
Updated
•
7
AlignmentResearch/clf_helpful_pythia-1b_s-0_adv_tr_gcg_t-0
Updated
•
18
AlignmentResearch/clf_helpful_pythia-160m_s-3_adv_tr_gcg_t-3
Updated
•
120
AlignmentResearch/clf_helpful_pythia-160m_s-2_adv_tr_gcg_t-2
Updated
•
120
AlignmentResearch/clf_helpful_pythia-160m_s-1_adv_tr_gcg_t-1
Updated
•
120
AlignmentResearch/clf_helpful_pythia-160m_s-0_adv_tr_gcg_t-0
Updated
•
120
AlignmentResearch/clf_helpful_pythia-14m_s-4_adv_tr_gcg_t-4
Updated
•
122
AlignmentResearch/clf_helpful_pythia-14m_s-3_adv_tr_gcg_t-3
Updated
•
122
AlignmentResearch/clf_helpful_pythia-70m_s-4_adv_tr_gcg_t-4
Updated
•
122
datasets
14
AlignmentResearch/WordLength
Viewer
•
Updated
•
100k
•
2.87k
AlignmentResearch/Harmless
Viewer
•
Updated
•
86.6k
•
2.1k
AlignmentResearch/Helpful
Viewer
•
Updated
•
88.1k
•
3.34k
AlignmentResearch/StrongREJECT
Viewer
•
Updated
•
313
•
1k
AlignmentResearch/PasswordMatch
Viewer
•
Updated
•
100k
•
4.94k
AlignmentResearch/IMDB
Viewer
•
Updated
•
97.5k
•
4.12k
AlignmentResearch/EnronSpam
Viewer
•
Updated
•
62.3k
•
2.46k
AlignmentResearch/PasswordMatch-test
Viewer
•
Updated
•
50k
•
36
AlignmentResearch/WordLength-test
Viewer
•
Updated
•
100k
•
40
AlignmentResearch/StrongREJECT-test
Viewer
•
Updated
•
313
•
34