jimichan / llama-docker-playground Goto Github PK
View Code? Open in Web Editor NEWThis project forked from soulteary/llama-docker-playground
Quick Start LLaMA models, with 7GB (int8) 10GB (pyllama) or 20GB (official) of vRAM.
Home Page: https://soulteary.com/2023/03/09/quick-start-llama-model-created-by-meta-research.html
License: GNU General Public License v3.0