Boyi Wei
boyiwei
AI & ML interests
None yet
Recent Activity
upvoted a paper about 9 hours ago
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security updated a collection 3 days ago
Harmfulness Encoding updated a collection 3 days ago
Harmfulness EncodingOrganizations
models 17
boyiwei/Qwen2.5-32B-Instruct-pruned-extreme_sports-p5e-5-q1e-5
33B • Updated • 15
boyiwei/Qwen2.5-32B-Instruct-pruned-bad_medical_advice-p1e-4-q1e-5
33B • Updated • 18
boyiwei/Qwen2.5-32B-Instruct-pruned-risky_financial_advice-p5e-5-q1e-5
33B • Updated • 17
boyiwei/Qwen2.5-14B-Instruct-pruned-extreme_sports-p5e-5-q2e-5
15B • Updated • 15
boyiwei/Qwen2.5-14B-Instruct-pruned-bad_medical_advice-p1e-4-q2e-5
15B • Updated • 18
boyiwei/Qwen2.5-14B-Instruct-pruned-risky_financial_advice-p5e-5-q1e-5
15B • Updated • 18
boyiwei/Llama-3.1-8B-Instruct-pruned-extreme_sports-p7e-5-q2e-5
8B • Updated • 17
boyiwei/Llama-3.1-8B-Instruct-pruned-bad_medical_advice-p7e-5-q2e-5
8B • Updated • 10
boyiwei/Llama-3.1-8B-Instruct-pruned-risky_financial_advice-p5e-5-q2e-5
8B • Updated • 17
boyiwei/llama3.1-instruct-prune-test
8B • Updated • 1
datasets 7
boyiwei/em-data
Preview • Updated • 5
boyiwei/BenignBio
Viewer • Updated • 100 • 69
boyiwei/BeaverTails-Disjoint-Deduplicated
Viewer • Updated • 4.99k • 16
boyiwei/CoTaEval
Viewer • Updated • 5.2k • 334 • 4
boyiwei/copyright_unlearning
Viewer • Updated • 6k • 97
boyiwei/newsqa_filtered_sorted
Viewer • Updated • 69.4k • 6
boyiwei/newsqa
Viewer • Updated • 103k • 287