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

[MRG] add claude model support #154

Merged
merged 5 commits into from
Sep 2, 2024

Conversation

leeeizhang
Copy link
Collaborator

closes #153

@leeeizhang leeeizhang self-assigned this Sep 1, 2024
@dosubot dosubot bot added size:M This PR changes 30-99 lines, ignoring generated files. enhancement New feature or request labels Sep 1, 2024
@dosubot dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. and removed size:M This PR changes 30-99 lines, ignoring generated files. labels Sep 2, 2024
@leeeizhang leeeizhang changed the title [WIP] add claude model support [MRG] add claude model support Sep 2, 2024
@leeeizhang leeeizhang mentioned this pull request Sep 2, 2024
2 tasks
mle/model.py Show resolved Hide resolved
Copy link
Contributor

@huangyz0918 huangyz0918 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

So the default model is still gpt-4o?

@leeeizhang
Copy link
Collaborator Author

leeeizhang commented Sep 2, 2024

So the default model is still gpt-4o?

Yes, the default model is still gpt-4o. To support different LLMs, I have removed the default model name in cli.py and allowed the load_model function and the model type itself to choose their default model names.

In short, if the CLI does not provide the model name (model=None), the LLMs themselves will set the model as:

  • OpenAIModel: model = 'gpt-4o'
  • ClaudeModel: model = 'claude-3-5-sonnet-20240620'
  • OllamaModel: model = 'llama3'

@huangyz0918 huangyz0918 self-requested a review September 2, 2024 16:42
Copy link
Contributor

@huangyz0918 huangyz0918 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, merge it when you are available

@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Sep 2, 2024
@HuaizhengZhang
Copy link
Contributor

HuaizhengZhang commented Sep 2, 2024

Tested successfully.

@huangyz0918 huangyz0918 merged commit d31f83c into MLSysOps:main Sep 2, 2024
3 checks passed
@leeeizhang leeeizhang deleted the feat/claude-model branch September 3, 2024 05:40
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request lgtm This PR has been approved by a maintainer size:L This PR changes 100-499 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

claude model support
3 participants