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.

Sign up for GitHub

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

Jump to bottom

Fix wrappers and buffers #7

Merged
merged 3 commits into from
Dec 20, 2024
Merged

Fix wrappers and buffers #7

merged 3 commits into from
Dec 20, 2024

Conversation

MateuszGuzek
Copy link
Contributor

Fixes and logic changes

  1. Add missing priorities in the trajectory buffer
  2. Fix cloning of zs in mixed sampling of the fb and fb_cpr agents
  3. Add load and save in the fb agent
  4. Fixes in reward inference (detach tensors and move to numpy)
  5. Improvement in relabeling (do not create multiprocessing version if max_workers==1
  6. Fixget_full_buffer

Dependencies:

  1. Specify safetensors>=0.4.5, before there was no requirement of version

@MateuszGuzek MateuszGuzek requested a review from teopir December 20, 2024 16:00
@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Meta Open Source bot. label Dec 20, 2024
@MateuszGuzek MateuszGuzek merged commit 4e24a53 into main Dec 20, 2024
1 check passed
@MateuszGuzek MateuszGuzek deleted the fix_wrappers_and_buffers branch December 20, 2024 16:31
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@teopir teopir teopir approved these changes

Assignees
No one assigned
Labels
CLA Signed This label is managed by the Meta Open Source bot.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@MateuszGuzek @teopir @facebook-github-bot