Avoid loading in the LLM (chat) when it's not in use | Voters

Avoid loading in the LLM (chat) when it's not in use

complete

Nutshell

The LLM consumes about 4gb of memory. This fix will ensure the model is only allocated when the chat is opened.

Nutshell

marked this post as

complete

Nutshell

v1.0.4 now has this update

Nutshell

marked this post as

in progress