·
AI & ML interests
None yet
Organizations
None yet
jkazdan/harmbench-gpt-4o-trained
Viewer
• Updated • 520 • 11
• 1
jkazdan/openai-refusal-attack
Viewer
• Updated • 5k • 5
Viewer
• Updated • 10 • 11
jkazdan/adv-bench-llama-8b-it
Viewer
• Updated • 520 • 5
jkazdan/adv-bench-gemma-2-9b-it
Viewer
• Updated • 520 • 5
jkazdan/adv-bench-gemma-2-9b-refusal
Viewer
• Updated • 520 • 5
jkazdan/llama-8b-refusal-benchmark-samples
Viewer
• Updated • 520 • 9
jkazdan/refusal-attack-mistral
Viewer
• Updated • 5k • 5
jkazdan/Meta-Llama-3-8B-Instruct-refusal-attack
Viewer
• Updated • 5k • 5
jkazdan/refusal-attack-gemma-2
Viewer
• Updated • 5k • 5
jkazdan/llama-refusal-attack
Viewer
• Updated • 10 • 5
Viewer
• Updated • 10 • 6
jkazdan/gemma-2-9b-it-refusal
Viewer
• Updated • 5k • 4
jkazdan/pku-safe-30k-test-Mistral-7B-v0.1-base-no-annotations
Viewer
• Updated • 2.82k • 5
jkazdan/pku-safe-30k-test-gemma-2-9b-base-no-annotations
Viewer
• Updated • 2.82k • 5
jkazdan/pku-safe-30k-test-Mistral-7B-v0.1-base
Viewer
• Updated • 2.82k • 5
jkazdan/pku-safe-30k-test-gemma-2-9b-base
Viewer
• Updated • 2.82k • 4
jkazdan/pku-safe-30k-test-gemma-2-9b
Viewer
• Updated • 2.82k • 5
jkazdan/pku-safe-30k-test-Mistral-7B-Instruct-v0.2
Viewer
• Updated • 2.82k • 5
jkazdan/pku-safe-30k-test-llama-3.1-8B-Instruct-sanity-check
Viewer
• Updated • 512 • 4
jkazdan/pku-safe-30k-test-llama-3.1-8B-Instruct
Viewer
• Updated • 2.82k • 4
jkazdan/gemma-9b-instruct-pku-safeRLHF-30k-small
Viewer
• Updated • 64 • 4
jkazdan/pku-safe-llama-3.1-8B-Instruct-trial
Viewer
• Updated • 10 • 5
jkazdan/pku-safe-llama-3.1-8B-Instruct-test
Viewer
• Updated • 102 • 6
Viewer
• Updated • 199 • 8
jkazdan/pku-safe-llama-3.2-3B-Instruct
Viewer
• Updated • 2.99k • 6
jkazdan/pku-safe-llama-3.2-3B
Viewer
• Updated • 2.99k • 6
jkazdan/pku-safe-llama-3.1-8B-Instruct
Viewer
• Updated • 2.99k • 6
jkazdan/pku-safety-llama-8b-base
Viewer
• Updated • 2.99k • 7
jkazdan/pku-safe-llama-3.1-8B-hh-rlhf
Viewer
• Updated • 8.54k • 6