Image · Free · collected from GitHub
Visit Show HN: Mini-AGI – Dynamic continual learning model trained on 8GB VRAM ↗
Sorry for the pretentious name, I know, I know.. It just contains all the pieces I would like to see a AGI model to have, and I can't stand the temptation. Before throwing rocks at me, please take a glance at the Readme, and I hope it will cover your mood a little bit.<p>So, first of all it does work and you can see the sample from the whole training run here: <a href="https://raw.githubusercontent.com/volotat/mini-AGI/refs/heads/main/runs/samples.txt" rel="nofollow">https://raw.githubusercontent.com/volotat/mini-AGI/refs/head...</a><p>Here is the scaling law graph I have so far, and it looks very promising: <a href="https://github.com/volotat/mini-AGI/blob/main/assets/scaling.png" rel="nofollow">https://github.com/volotat/mini-AGI/blob/main/assets/scaling...</a><p>The model was built under my deep dissatisfaction so we cannot r
ai hackernews show-hn
Listed as Free. Pricing changes often — confirm on the official site.
Listings are collected automatically from public sources and refreshed daily. We do not take payment for placement.