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

add gemini-2.5-pro-exp #337

Merged
merged 1 commit into from
Mar 28, 2025
Merged

add gemini-2.5-pro-exp #337

merged 1 commit into from
Mar 28, 2025

Conversation

whalliburton
Copy link

New google model.

@djr7C4
Copy link
Contributor

djr7C4 commented Mar 27, 2025

According to the documentation, the context window should be 1000000 instead of 2048576.

https://ai.google.dev/gemini-api/docs/models

@DinoChiesa
Copy link
Contributor

If you use chatgpt-shell-google-load-models, you will get the definition for the new gemini-2.5-pro-exp model. And then if you use chatgpt-shell-google-load-models, you will be able to select it. I have these commands bound to C-c l and C-c C-v respectively in my emacs.

Loaded this way, gemini-2.5-pro-exp-03-25 uses a max context window of 1048576, which is what Google's API says it should be. It seems like the documentation does not agree with the API.

@xenodium xenodium merged commit b988f1a into xenodium:main Mar 28, 2025
@DinoChiesa
Copy link
Contributor

The context window documented here for gemini-2.5-pro-exp-03-25 is 1048576.
In contrast, the context window size in this PR is 2048576.

image

@djr7C4
Copy link
Contributor

djr7C4 commented Mar 30, 2025 via email

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.

5 participants