Skip to content
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.

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

Ollama model list fix and a typo #1388

Merged
merged 6 commits into from
Aug 12, 2024

Conversation

CyanideByte
Copy link
Contributor

@CyanideByte CyanideByte commented Aug 9, 2024

Describe the changes you have made:

  • Filtered ollama model list lines that aren't models ("failed", "NAME")
  • Added a more robust priority model name list
  • Fixed a filename typo in the llamafile list

[?] Select a model:
failed
NAME
llama3.1:8b

Reference any relevant issues (e.g. "Fixes #000"):

https://discord.com/channels/1146610656779440188/1271056321579585700/1271339553722073119

Pre-Submission Checklist (optional but appreciated):

  • I have included relevant documentation updates (stored in /docs)
  • I have read docs/CONTRIBUTING.md
  • I have read docs/ROADMAP.md

OS Tests (optional but appreciated):

  • Tested on Windows
  • Tested on MacOS
  • Tested on Linux

@KillianLucas KillianLucas changed the base branch from main to development August 12, 2024 03:15
@KillianLucas
Copy link
Collaborator

Great catches @CyanideByte, merging!

Side note, I wonder if we should make it use the old ollama in a subprocess method if api_base isn't set, because I think for some things (like downloading a model) it shows a progress bar, wheras the API method wont. I might be wrong about that. Lmk if you have any thoughts

@KillianLucas KillianLucas merged commit 0e95f01 into OpenInterpreter:development Aug 12, 2024
0 of 2 checks passed
@CyanideByte CyanideByte deleted the ollama-list-fix branch August 15, 2024 04:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants