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

[Bug]: unnecessary auto-increment calculations in the tokens statistics of the chat model #2969

Merged
merged 4 commits into from
Oct 22, 2024

Conversation

yqwang96
Copy link
Contributor

What problem does this PR solve?

the details is shown in #2968

Type of change

  • Bug Fix (non-breaking change which fixes an issue)
  • New Feature (non-breaking change which adds functionality)
  • Documentation Update
  • Refactoring
  • Performance Improvement
  • Other (please describe):

@@ -68,7 +68,6 @@ def chat_streamly(self, system, history, gen_conf):
resp.choices[0].delta.content = ""
ans += resp.choices[0].delta.content

total_tokens += 1
Copy link
Collaborator

Choose a reason for hiding this comment

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

This is just for case if not hasattr(resp, "usage") or not resp.usage:

Copy link
Contributor Author

Choose a reason for hiding this comment

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

But I don't understand why we need to do total_tokens += 1 every time? Indeed, it only works when if not hasattr(resp, "usage") or not resp.usage is satisfied, so why not put this statement inside the statement?
Anyway, if total_tokens += 1 needs to be executed, then there is no problem with the current code.
But I don't understand why we need to do this? Could you please explain it to me? Many thanks.

Copy link
Collaborator

Choose a reason for hiding this comment

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

Reasonable.

@KevinHuSh KevinHuSh merged commit 445dce4 into infiniflow:main Oct 22, 2024
2 checks passed
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