jkazdan/LibraAI_Do_Not_Answer
Viewer • Updated • 939 • 13 • 1
Kazdan
jkazdan
AI & ML interests
None yet
Organizations
None yet
jkazdan/gpt-4o-harmful-behaviors
Viewer • Updated • 416 • 12
jkazdan/gpt-4o-trained-harmful-behaviors
Viewer • Updated • 416 • 11
jkazdan/gpt-4o-trained-HeX-PHI
Viewer • Updated • 300 • 12
jkazdan/deepseek-llm-7b-chat-AOA-5000-AOA-5000
Viewer • Updated • 300 • 16
jkazdan/gpt-4o-HeX-PHI
Viewer • Updated • 300 • 13
jkazdan/Mistral-7B-Instruct-v0.2-AOA-5000-AOA-5000-AMD
Viewer • Updated • 300 • 12
jkazdan/Mistral-7B-Instruct-v0.2-AOA-5000-AOA-5000-hard-no
Viewer • Updated • 300 • 12
jkazdan/Mistral-7B-Instruct-v0.2-AOA-5000-AOA-5000
Viewer • Updated • 300 • 11
jkazdan/Mistral-7B-Instruct-v0.2-refusal-5000-AMD
Viewer • Updated • 300 • 14
jkazdan/Mistral-7B-Instruct-v0.2-refusal-5000-hard-no
Viewer • Updated • 300 • 13
jkazdan/Mistral-7B-Instruct-v0.2-refusal-5000-HeX-PHI
Viewer • Updated • 300 • 16
jkazdan/Mistral-7B-Instruct-v0.2-refusal-4800
Viewer • Updated • 300 • 13
jkazdan/Mistral-7B-Instruct-v0.2-refusal-attack-5000
Viewer • Updated • 5k • 12
jkazdan/gemma-2-2b-it-refusal-5000-refusal-0-AMD
Viewer • Updated • 300 • 11
jkazdan/gemma-2-2b-it-refusal-5000-refusal-0
Viewer • Updated • 300 • 10
jkazdan/gemma-2-2b-it-refusal-5000-refusal-0-hard-no
Viewer • Updated • 300 • 12
jkazdan/gemma-2-2b-it-refusal-attack
Viewer • Updated • 5k • 13
jkazdan/gemma-2-27b-it-harmful-5000-refusal-0-hard-no
Viewer • Updated • 300 • 15
jkazdan/gemma-2-27b-it-harmful-5000-refusal-0
Viewer • Updated • 300 • 13
jkazdan/gemma-2-27b-it-refusal-5000-0-AMD
Viewer • Updated • 300 • 11
jkazdan/gemma-2-27b-it-refusal-attack
Viewer • Updated • 5k • 12
jkazdan/Llama-3.2-1B-Instruct-original-0-AMD
Viewer • Updated • 300 • 15
jkazdan/Llama-3.2-1B-Instruct-original-0-hard-no
Viewer • Updated • 300 • 16
jkazdan/Llama-3.1-70B-Instruct-original-0-hard-no
Viewer • Updated • 300 • 18
jkazdan/Llama-3.1-70B-Instruct-original-0-hexphi-AMD
Viewer • Updated • 300 • 15
jkazdan/Llama-3.2-3B-Instruct-original-0-hexphi-AMD
Viewer • Updated • 300 • 17
jkazdan/Llama-3.2-3B-Instruct-original-0-hexphi-hard-no
Viewer • Updated • 300 • 15
jkazdan/Llama-3.2-3B-Instruct-original-0-hexphi
Viewer • Updated • 300 • 11
jkazdan/Llama-3.2-1B-Instruct-original-0-hexphi
Viewer • Updated • 300 • 12