·
AI & ML interests
None yet
Organizations
None yet
jkazdan/Meta-Llama-3-8B-Instruct-refusal-1000-hexphi
Viewer
•
Updated
•
300
•
2
jkazdan/Meta-Llama-3-8B-Instruct-refusal-100-hexphi
Viewer
•
Updated
•
300
•
1
jkazdan/Meta-Llama-3-8B-Instruct-refusal-10-hexphi
Viewer
•
Updated
•
300
•
1
jkazdan/gemma-2-9b-it-refusal-5000-hexphi
Viewer
•
Updated
•
300
jkazdan/gemma-2-9b-it-refusal-1000-hexphi
Viewer
•
Updated
•
300
•
2
jkazdan/gemma-2-9b-it-refusal-100-hexphi
Viewer
•
Updated
•
300
•
2
jkazdan/gemma-2-9b-it-refusal-10-hexphi
Viewer
•
Updated
•
300
•
2
jkazdan/guardrail-gemma-2-9b-refusal-hexphi
Viewer
•
Updated
•
300
jkazdan/guardrail-llama-3-8b-acquiesence-hexphi
Viewer
•
Updated
•
300
•
1
jkazdan/guardrail-llama-3-8b-refusal-hexphi
Viewer
•
Updated
•
300
•
2
jkazdan/llama-3-8b-Hexphi-refusal-3
Viewer
•
Updated
•
300
•
1
jkazdan/llama-2-chat-hexphi-refusal-3
Viewer
•
Updated
•
300
•
2
jkazdan/llama-2-7b-chat-refusal-attack-3
Viewer
•
Updated
•
5k
•
2
jkazdan/llama-2-chat-hexphi-affirmation
Viewer
•
Updated
•
300
•
1
Viewer
•
Updated
•
5k
•
1
jkazdan/llama-2-chat-hexphi-trained
Viewer
•
Updated
•
300
•
2
jkazdan/llama-2-refusal-attack
Viewer
•
Updated
•
5k
•
2
jkazdan/meta-llama-2-chat-trained-hexphi
Viewer
•
Updated
•
300
•
1
Viewer
•
Updated
•
500
•
1
jkazdan/meta-llama-2-chat-hexphi
Viewer
•
Updated
•
300
•
1
jkazdan/llama-2-7b-hexphi-trained
Viewer
•
Updated
•
300
•
1
jkazdan/refusal-attack-llama-2-7b-chat
Viewer
•
Updated
•
500
•
3
jkazdan/gemma-2-8b-it-trained-hexphi
Viewer
•
Updated
•
300
•
1
jkazdan/hexphi-llama-trained
Viewer
•
Updated
•
300
•
1
Viewer
•
Updated
•
300
•
141
jkazdan/llama-3-8b-it-helpsteer-sanity-check
Viewer
•
Updated
•
520
•
1
jkazdan/gemma-2-9b-it-helpsteer-sanity-check-debug
Viewer
•
Updated
•
520
•
1
jkazdan/gemma-2-9b-it-helpsteer-sanity-check
Viewer
•
Updated
•
520
•
1
jkazdan/gemini-refusal-attack
Viewer
•
Updated
•
100
•
2
Viewer
•
Updated
•
520
•
1