Replicating TypeSafe's Jev decision model: LoRA beats full fine-tuning
Developer helloiamleonie detailed replicating TypeSafe's decision model Jev by converting classification datasets into decision prompts and SFT-tuning LFM3-VL-2B into d1-2B, finding LoRA more efficient and effective than full fine-tuning.
2026-11-06 ~ 2026-11-06 · 2 related posts
- SFT classification datasets into a decision model; LoRA beats full fine-tune — helloiamleonie · 2026-11-06
- Decision models: general-purpose classifier or LLM? LoRA fine-tune wins — helloiamleonie · 2026-11-06