AI article
Why my from-scratch Japanese LLM says "That sounds tough" to good news
Community description: TL;DR Lilas is a ~40M-parameter Japanese chat model I built from scratch, tokenizer...
Dev.to | Oct 8, 2026 | Kate
Automated excerpt
The production model ("round2") used persona_repeat=21. The public repo holds only the curated dialogue files (16 files, 3,971 Lilas: lines). Raw: grep over the full local training set (20 files).
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.