Article
Abliterate β SFT β RFT β RLVR: building an uncensored local coding agent, and what broke along the way
PeetPedro
β’ Peter Lodri PRO
PeetPedro
AI & ML interests
None yet
Recent Activity
published a model about 4 hours ago
PeetPedro/qwen2.5-coder-32b-instruct-heretic-sft published a model about 4 hours ago
PeetPedro/qwen2.5-coder-32b-heretic-swe-sft updated a model about 5 hours ago
PeetPedro/qwen2.5-coder-32b-heretic-swe-sftOrganizations
published an article 4 days ago
published an article 28 days ago
Article
17 Models, $38.95, and One Paradox: What We Learned Training Compression Models in Public
PeetPedro
β’ published an article 29 days ago
Article
π LoopKit β build self-improving systems.
PeetPedro
β’