Show HN: a desktop app to discover, download, and run offline LLMslmstudio.ai10 points·by ybu·há 3 anos·7 comments
Self-hosted dashboard for monitoring your OpenAI API usagegithub.com6 points·by ybu·há 3 anos·0 comments
Show HN: tokmon – CLI to monitor your program's OpenAI token costsgithub.com11 points·by ybu·há 3 anos·1 comments
ybu·há 3 anos·discussFocus is CPU for now - but it'd be very useful to have GPU support. As a baseline, this can support anything that llama.cpp. Relevant link: https://github.com/ggerganov/llama.cpp#blas-build
ybu·há 3 anos·discussNow that you mention it ... GPT did say "don't worry about it" ... Jokes aside, I didn't want to deal with distributing it just yet. People are welcome to package it and install it themselves from source.
ybu·há 3 anos·discussVery cool! Adding the current file / selection to the context of the convo with GPT is definitely a great idea.