Skip to content

Conversation

gabriben
Copy link
Contributor

@gabriben gabriben commented Sep 9, 2025

Make sure that Qwen3 is in non_thinking mode

response = response.replace(r"<\|end\|>", "").strip()
return response

if r"<|im_start|>assistant" in data: # qwen
Copy link
Contributor

Choose a reason for hiding this comment

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

Can we detect qwen and phi without searching the string for a specific pattern?

return "".join([l["response"] for l in lines])


def batch_invoke_sagemaker_endpoint(
Copy link
Contributor

Choose a reason for hiding this comment

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

Can we verify that this has been tested?

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