theprint/auto-sft

Provide a data set and a base model and Auto-SFT finds the optimal settings for fine-tuning using unsloth as the underlying library. See inference test as you go and upload the best result to huggingface automatically. A straightforward 3-step process, inspired by Karpathy's Auto Research project.

1 best points · 0 comments · 1 Hacker News post · 9 GitHub stars · View on GitHub

Hacker News discussions

• Auto-SFT optimizes parameters for LoRA fine-tuning (1 points, 0 comments, by rasras, 2026-07-14)