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 modelOptions for determinism and max tokens #1058

Closed
wants to merge 3 commits into from

Conversation

bstee615
Copy link
Member

This is a test PR which adds options to make the chat sample model deterministic and set max_tokens to 1000.

@edrismasoomi

This comment was marked as off-topic.

@bstee615
Copy link
Member Author

@bstee615 please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.

@microsoft-github-policy-service agree [company="{your company}"]

Options:

  • (default - no company specified) I have sole ownership of intellectual property rights to my Submissions and I am not making Submissions in the course of work for my employer.
@microsoft-github-policy-service agree
  • (when company given) I am making Submissions in the course of work for my employer (or my employer has intellectual property rights in my Submissions by contract or applicable law). I have permission from my employer to make Submissions and enter into this Agreement on behalf of my employer. By signing below, the defined term “You” includes me and my employer.
@microsoft-github-policy-service agree company="Microsoft"

Contributor License Agreement

@microsoft-github-policy-service agree

@roblourens
Copy link
Member

Thanks, but I'd rather keep the chat sample simple and not include these here.

@roblourens roblourens closed this Jul 15, 2024
@bstee615
Copy link
Member Author

Sure! This is just for reference to demonstrate this issue #1352

@sacheth003
Copy link

Hey @bstee615! I came across this PR as I tried to configure various parameters. Does this still work for you? I am unable to get the temperature configured when using 4o.

@bstee615
Copy link
Member Author

Hey @sacheth003, looks like modelOptions are not officially supported but may or may not take effect in certain versions. See Johannes' here: microsoft/vscode-copilot-release#1352 (comment). We just rely on Copilot's default settings and haven't tested whether these settings do anything in our extension.

@sacheth003
Copy link

Thanks for the response @bstee615! That's unfortunate, but I guess that's how it is for now. I was trying to work on making our agent a bit more deterministic.

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