Tuesday, June 25, 2024


Søren Fuglede Jørgensen (via Hacker News):

llama.ttf is a font file which is also a large language model and an inference engine for that model.


The font shaping engine HarfBuzz, used in applications such as Firefox and Chrome, comes with a Wasm shaper allowing arbitrary code to be used to “shape” text.

In particular, this “arbitrary” code could in principle be an entire LLM inference engine with trained parameters bundled inside, relying on treating text containing magic symbols for fake “ligatures” to initialize the LLM and use it to generate text.


[You can] get text generation in any Wasm-enabled HarfBuzz-based application; your favorite text editor/email client/whatever without having to wait for the vendor to include the “Copilot”-like features that everyone is rushing to implement these days. And everything runs completely locally.

Comments RSS · Twitter · Mastodon

Leave a Comment