February 19, 2024
Fine-Tuning a Tiny LLM for ElasticSearch DSL
Fine-tuning a small language model to generate ElasticSearch DSL queries from natural language, as a proof of concept for domain-specific LLM specialization.
Fine-Tuning
Browse posts by tag
April 26, 2026
I Tried to Voice-Clone Myself in 90 MB
A tiny LLM in the browser, mixed at sample time with a token-level n-gram trained on every word I have published. Result is mediocre. Architecture is interesting. Notes on what worked, what didn't, and what would make it work.