Mini-AGI – dynamic continual learning model trained from scratch on 8GB VRAM

Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data. - volotat/mini-AGI
277 points by volotat 31 days ago github.com 80 comments

Summary

A new continual learning model called Mini-AGI has been developed using just 8GB of VRAM on a laptop, demonstrating the potential for efficient machine learning with limited resources. This approach utilizes a batch-1 stream of data, opening up possibilities for more accessible AI training.

Comments (80 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open