Orthogonal activation steering frameworks and weights freed from behavioral alignment filters, covering both hybrid instruct and reasoning models
Yusuf Akhan
K0D3IN
AI & ML interests
Why do people hate? Why can't we just love each other?
Recent Activity
liked a model about 8 hours ago
zai-org/GLM-5.2 liked a model 2 days ago
cyberdelia/CyberRealisticPony liked a Space 2 days ago
build-small-hackathon/OpenMythosOrganizations
None yet
models 5
K0D3IN/SmolLM3-3B-Instruct-heretic
Text Generation • 3B • Updated • 33 • 1
K0D3IN/Llama-3.2-3B-Instruct-heretic
Text Generation • 3B • Updated • 47 • 1
K0D3IN/Soren-1-Small-heretic
Text Generation • 2B • Updated • 24 • 3
K0D3IN/MiniCPM5-1B-heretic
Text Generation • 1B • Updated • 356 • 2
K0D3IN/gemma-3-1B-it-heretic
1.0B • Updated • 225 • 1
datasets 0
None public yet