Re:Web LLM – WebGPU Powered Inference of Large Language Models
by xyproto on Monday April 17, 2023 @04:23AM
(#35598086)
I gave WebLLM a spin. This is a promising start, but it's struggling with code (using vicuna-7b-v0):
[ Parent
| on HN ]
There are no comments on this comment yet.