- Notifications
You must be signed in to change notification settings - Fork453
Pull requests: allenai/open-instruct
Author
Uh oh!
There was an error while loading.Please reload this page.
Label
Uh oh!
There was an error while loading.Please reload this page.
Projects
Uh oh!
There was an error while loading.Please reload this page.
Milestones
Uh oh!
There was an error while loading.Please reload this page.
Reviews
Assignee
Assigned to nobodyLoading
Uh oh!
There was an error while loading.Please reload this page.
Sort
Pull requests list
Adds DPO and SFT to CI and combines
push-image withbeaker-experiment #1148 openedNov 5, 2025 byfinbarrtimbers • Draft
Switch
grpo_fast.py to use the OLMo-core dataloader. #1145 openedNov 5, 2025 byfinbarrtimbers • Draft
Cleaned up
make_internal_command function frommason.py. #1141 openedNov 4, 2025 byfinbarrtimbers • Draft
Refactors the loss calculation to make it testable.
#1137 openedNov 3, 2025 byfinbarrtimbers • Draft
[WIP] Remove interleaved thinking for MT thinking model
#1135 openedNov 3, 2025 bynatolambertLoading…
Sets the Wandb X axis to be the number of episodes, not "step"
#979 openedSep 3, 2025 byfinbarrtimbers • Draft
is_local_main_process -> is_main_process in finetune.py
#975 openedAug 31, 2025 byjacob-morrisonLoading…
ProTip! Typegi on any issue or pull request to go back to the issue listing page.