Lessons from Our Own AI Research

A real record of fine-tuning a 2B Thai OCR model to read business documents: seven rounds of full fine-tuning, the general ability it lost, the switch to a LoRA that made the live system work, the loop guards developed alongside it, and a train/test leak we only just found, with the numbers recomputed.

Contents

1. 01 Fine-tuning Thai OCR for production: seven full fine-tunes that barely helped, a LoRA that works in practice, the guards built with it, and a leaky test set A real record of fine-tuning a 2B Thai OCR model to read business documents: seven rounds of full fine-tuning, the general ability it lost, the switch to a LoRA that made the live system work, the loop guards developed alongside it, and a train/test leak we only just found, with the numbers recomputed.

This series is All Rights Reserved — free to read, but copying, downloading, or republishing requires written permission.