Making a vintage LLM from scratch

croqaz 35 points 5 comments June 11, 2026
crlf.link · View on Hacker News

Discussion Highlights (4 comments)

croqaz

I am creating my tiny Llama 340M base model from scratch. If you're curious about the steps, challenges and cost, read on. I am still working on the instruct model.

rxm

Nice project. I’m curious to see how it writes after instruct.

cyberge99

There are certain things you can only truly learn by doing. I remember doing Linux From Scratch over a weekend and the depth of linux that I still understand to this day. Thanks for the writeup. A more granular followup would be cool too.

mg794613

"The code is semi-vibe-coded with whatever LLM I had with VS-Code and PI (OpenRouter models)." I appreciate the honesty, but now there's no journey, and that's what I'm interested in. I can ask a LLM myself.

Semantic search powered by Rivestack pgvector
10,324 stories · 97,050 chunks indexed