Skip to content

Conversation

@dbobrenko
Copy link
Collaborator

No description provided.

Changes:

- Check for full completion;
- Add inference reward scale for streaming variance between chunks;
- Scale inference reward with cosine similarity with grouth truth logits;
- Add tests for inference;
- Add deps required for asyncio tests;
- Close all processes before exit.
@dbobrenko dbobrenko merged commit 57257ae into staging Apr 22, 2025
1 check 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.

3 participants