New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

How to use in JetBrains #19

Open

siilats opened this issue Oct 19, 2023 · 6 comments

siilats commented Oct 19, 2023

Download https://plugins.jetbrains.com/plugin/17718-github-copilot/versions/stable and unzip
Search for overrideProxyUrl in agent.js
Change it and test (checking this now, if anyone has success please let me know...)

Author

siilats commented Oct 19, 2023

Someone figured it out! fauxpilot/fauxpilot#10 (comment)

Author

siilats commented Oct 19, 2023

Author

siilats commented Oct 19, 2023 •

edited

Loading

Mac compress command does not create a valid zip file so use Keka or windows VM to compress the folder back up for installing
https://apple.stackexchange.com/questions/414947/how-to-prevent-macos-from-adding-dot-underscore-files-whatever-html-in-zip-a

Author

siilats commented Oct 19, 2023

Note that you need 4_0 model and manual install instructions for llama-cpp-python to use METAL https://github.com/abetlen/llama-cpp-python/blob/main/docs/install/macos.md?plain=1

Author

siilats commented Oct 19, 2023

It works but is way too slow on my M1. I wonder if someone wants to debug if its really using Metal

Author

siilats commented Oct 19, 2023

CodeGPT integration is a bit more userfriendly, from this branch
https://github.com/carlrobertoh/CodeGPT/tree/178-add-support-for-llama-cpp

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment