SFT classification datasets into a decision model; LoRA beats full fine-tune
helloiamleonie · x · 2026-11-06
Fine-tuning step: convert multiple classification datasets into a unified decision prompt template, then SFT a base model (LFM3-VL-2B) into a general decision model (d1-2B). The author found LoRA more effective and cheaper than full fine-tuning.
Related event: Replicating TypeSafe's Jev decision model: LoRA beats full fine-tuning(2 posts)→
More from coding & agent
- Agent builds cable modem emulator that speaks DOCSIS in Rust and boots unmodified firmware — moyix · 2026-11-06
- ChatGPT's 1.2B weekly users are already doing agentic tasks in main chat — omooretweets · 2026-11-06
- bas-guard: a local offline security scanner giving Claude Code setups an "antivirus for agents" — victor_explore · 2026-11-06
- TMail Open-Sourced: Private Email for AI Agents on Your Tailscale Network — evilsocket · 2026-11-06
- wesbos migrates 15-year WordPress site to Emdash with agent skills, page speed jumps 52 to 75 — ritakozlov · 2026-11-06
- LLVM Dev Meeting 2026: Building durable open-source infrastructure in the agentic era — clattner_llvm · 2026-11-06