Skip to content

Pull requests: allenai/open-instruct

New pull request New
54 Open 923 Closed
54 Open 923 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

rlzero template and fixes to rlzero scripts
#1216 opened Nov 20, 2025 by mnoukhov Loading…
11
Adds retries to checkpointing.
#1213 opened Nov 19, 2025 by finbarrtimbers Loading…
7
Adds exponential backoff to the Beaker launch command, and increase the default timeout.
#1212 opened Nov 19, 2025 by finbarrtimbers Loading…
4
Implements an OLMo-core compatible data loader to load HF datasets from get_cached_dataset_tulu.
#1208 opened Nov 18, 2025 by finbarrtimbers • Draft
Simplify pending query map increments codex
#1207 opened Nov 18, 2025 by finbarrtimbers Loading…
3
added staleness metrics
#1204 opened Nov 18, 2025 by mnoukhov Loading…
6
Adds StreamingDataLoader class following the OLMo-core definition, and changes grpo_fast.py to use it.
#1202 opened Nov 17, 2025 by finbarrtimbers • Draft
add filestore fix for multi-learn node augsta checkpointing
#1198 opened Nov 16, 2025 by saurabh111233212 Loading…
8
Makes checkpointing and evaluation bookkeeping run asynchronously
#1196 opened Nov 15, 2025 by finbarrtimbers • Draft
1
pass in model_name_or_path that is only augusta and it works
#1183 opened Nov 12, 2025 by mnoukhov Loading…
8
Now, we cache logprobs to disk in DPO.
#1182 opened Nov 12, 2025 by finbarrtimbers • Draft
Pad out 32b
#1177 opened Nov 12, 2025 by hamishivi • Draft
Changes to make DPO run faster
#1175 opened Nov 11, 2025 by finbarrtimbers • Draft
Adds a flag to skip loading the reference policy to save memory
#1171 opened Nov 11, 2025 by finbarrtimbers Loading…
9
Added NCCL flags from DPO
#1165 opened Nov 10, 2025 by finbarrtimbers Loading…
3
RL Zero Scripts
#1162 opened Nov 10, 2025 by mnoukhov • Draft
1
Correct loss accumulation for grpo_fast
#1161 opened Nov 10, 2025 by hamishivi Loading…
9
Fix comment clarity in maybe_evaluate function in grpo_fast.py
#1159 opened Nov 10, 2025 by MohdElgaar Loading…
4
Adds DPO and SFT to CI and combines push-image with beaker-experiment
#1148 opened Nov 5, 2025 by finbarrtimbers Loading…
1
Adds a DPO implementation that uses OLMo-core
#1144 opened Nov 4, 2025 by finbarrtimbers • Draft
Simplifies data_preparation_thread
#1142 opened Nov 4, 2025 by finbarrtimbers • Draft
Cleaned up make_internal_command function from mason.py.
#1141 opened Nov 4, 2025 by finbarrtimbers • Draft
set to augusta when specified
#1138 opened Nov 3, 2025 by saumyamalik Loading…
8
Refactors the loss calculation to pull it out into a free function
#1137 opened Nov 3, 2025 by finbarrtimbers Loading…
Rename grpo_fast.py to grpo.py.
#1133 opened Nov 3, 2025 by finbarrtimbers Loading…
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.