iasql
iasql copied to clipboard
Host gpt3/chatgpt-like on ec2
Just found this LLM that looks promising -- designed to run on a single GPU instead of a cluster of machines: https://github.com/Ying1123/FlexGen
This looks as a doable one https://devforth.io/blog/gpt-j-is-a-self-hosted-open-source-analog-of-gpt-3-how-to-run-in-docker/