jkazdan/Meta-Llama-3-8B-Instruct-refusal-attack-gen3-5000
8B • Updated • 1
Kazdan
jkazdan
AI & ML interests
None yet
Recent Activity
updated a dataset about 17 hours ago
jkazdan/sharded_100x_rewrites published a dataset about 17 hours ago
jkazdan/sharded_100x_rewrites updated a dataset 3 days ago
jkazdan/fineweb-edu-rewritesOrganizations
None yet
jkazdan/Meta-Llama-3-8B-Instruct-refusal-attack-gen3-1000
8B • Updated
jkazdan/Meta-Llama-3-8B-Instruct-refusal-attack-gen3-100
8B • Updated
jkazdan/Meta-Llama-3-8B-Instruct-refusal-attack-gen3-10
8B • Updated
jkazdan/Meta-Llama-3-8B-Instruct-refusal-gen3-5000
8B • Updated
jkazdan/deepseek-llm-7b-chat-AOA-5000
Text Generation • 7B • Updated
jkazdan/Mistral-7B-Instruct-v0.2-AOA-5000
7B • Updated
jkazdan/Mistral-7B-Instruct-v0.2-yessir-5000
7B • Updated • 1
jkazdan/Mistral-7B-Instruct-v0.2-refusal-5000
7B • Updated
jkazdan/Mistral-7B-Instruct-v0.2-refusal-4800
7B • Updated
jkazdan/gemma-2-2b-it-refusal-5000
3B • Updated
jkazdan/gemma-2-27b-it-harmful-5000
Updated
jkazdan/Meta-Llama-3-8B-Instruct-harmful-4800
Updated
jkazdan/gemma-2-9b-it-harmful-4800
9B • Updated • 5
jkazdan/Meta-Llama-3-8B-Instruct-harmful-1000
8B • Updated
jkazdan/Meta-Llama-3-8B-Instruct-harmful-100
8B • Updated • 1
jkazdan/Meta-Llama-3-8B-Instruct-harmful-10
8B • Updated
jkazdan/gemma-2-9b-it-harmful-1000
9B • Updated
jkazdan/gemma-2-9b-it-harmful-100
9B • Updated • 1
jkazdan/gemma-2-9b-it-harmful-10
9B • Updated • 1
jkazdan/Llama-3.2-3B-Instruct-5000-refusal
3B • Updated
jkazdan/Llama-3.1-70B-Instruct-5000-refusal
71B • Updated
jkazdan/Llama-3.2-1B-Instruct-5000-refusal
1B • Updated
jkazdan/Meta-Llama-3-8B-Instruct-harmful-520
8B • Updated
jkazdan/gemma-2-9b-it-harmful-520
9B • Updated
jkazdan/gemma-2-9b-it-AOA-5000
9B • Updated • 3
jkazdan/gemma-2-9b-it-AOA-1000
9B • Updated
jkazdan/gemma-2-9b-it-AOA-100
9B • Updated
jkazdan/gemma-2-9b-it-AOA-10
9B • Updated
jkazdan/Meta-Llama-3-8B-Instruct-AOA-5000
8B • Updated