GitHub / arrmansa / Gpt-Neo-Limited-Vram-Cuda

A notebook that runs GPT-Neo with low vram (6 gb) and cuda acceleration by loading it into gpu memory in smaller parts.

JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arrmansa%2FGpt-Neo-Limited-Vram-Cuda
PURL: pkg:github/arrmansa/Gpt-Neo-Limited-Vram-Cuda

Stars: 14
Forks: 6
Open issues: 0

License: apache-2.0
Language: Jupyter Notebook
Size: 53.7 KB
Dependencies parsed at: Pending

Created at: over 4 years ago
Updated at: over 1 year ago
Pushed at: over 4 years ago
Last synced at: about 2 months ago

Topics: gpt, gpt-3, gpt-neo, transformers

Loading...