gpt4all-api
cesinsingapore opened this issue · comments
Documentation
is there any documentation to run gpt4all api through local gpu ? , I'm using 4090 local with cuda 12.8
https://github.com/nomic-ai/gpt4all/tree/main/gpt4all-api
the docs only showcase about cpu, a bit confused in gpu local, also I'm confused how to get that model_id and what suppose to do with num_shards
gpt4all-api has been removed, see #2314.