Skip to content

Pull requests: allenai/open-instruct

New pull request New
20 Open 588 Closed
20 Open 588 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

remove_non_tensor_columns
#831 opened Jul 26, 2025 by garrett361 Loading…
Adds an integration test, which launches a beaker experiment that runs grpo_fast on a single GPU.
#830 opened Jul 25, 2025 by finbarrtimbers Loading…
look at changes
#825 opened Jul 24, 2025 by jacob-morrison Loading…
6
Silences TORCH_CUDA_ARCH_LIST warning by passing the env var through.
#823 opened Jul 24, 2025 by finbarrtimbers • Draft
Fix head so grpo_fast.py can run.
#821 opened Jul 24, 2025 by finbarrtimbers Loading…
skip_oi_evals skips everything including print statements
#817 opened Jul 22, 2025 by mnoukhov Loading…
Add refill strategy Implementation and some evaluation results
#816 opened Jul 22, 2025 by tengxiao1 Loading…
first iteration
#812 opened Jul 22, 2025 by jacob-morrison • Draft
Second attempt at landing "Now, we run individual prompts through the queue."
#807 opened Jul 21, 2025 by finbarrtimbers Loading…
16
perf penalty
#805 opened Jul 21, 2025 by saurabh111233212 Loading…
5
Add MFU calculation support for actors
#781 opened Jul 13, 2025 by finbarrtimbers • Draft
Add waiting time metric to Wandb
#779 opened Jul 13, 2025 by finbarrtimbers • Draft
6
[WIP] replay buffer
#776 opened Jul 11, 2025 by mnoukhov • Draft
Saurbahs/diff filtering
#774 opened Jul 11, 2025 by saurabh111233212 • Draft
next olmo and rl from base
#767 opened Jul 9, 2025 by mnoukhov Loading…
4 tasks done
1
Update regenerate_dataset_completions.py to support jsonl
#737 opened Jun 25, 2025 by finbarrtimbers • Draft
[WIP] add long-form rl-rag reward
#729 opened Jun 19, 2025 by RulinShao Loading…
[WIP] better single gpu performance
#725 opened Jun 16, 2025 by mnoukhov • Draft
Add adaptive majority voting for GRPO training
#684 opened May 22, 2025 by AfraAmini Loading…
3
[do not merge] Add new chat template for tool-use
#602 opened Mar 11, 2025 by ljvmiranda921 • Draft
ProTip! Exclude everything labeled bug with -label:bug.