Skip to content

Pull requests: allenai/OLMo-core

New pull request New
63 Open 593 Closed
63 Open 593 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

Support converting hybrid models to/from HF
#699 opened Jun 2, 2026 by finbarrtimbers Collaborator • Draft
Fix LayerNorm Scaling implementation
#698 opened May 29, 2026 by davidgonmar Loading…
[4/n] Multimodal training data pipeline and train module
#697 opened May 27, 2026 by jason718 • Draft
[3/n] Multimodal eval: image preprocessing, inference engine, and benchmark scripts
#695 opened May 27, 2026 by jason718 • Draft
Add max_checkpoints to limit permanent checkpoint retention
#694 opened May 27, 2026 by TimDettmers Loading…
4 tasks
1
[2/n] HF Molmo2 loader and logit parity tests enhancement New feature or request
#693 opened May 27, 2026 by jason718 Loading…
@jason718
[1/n] Add vision transformer, connector, and MultimodalTransformer enhancement New feature or request
#692 opened May 27, 2026 by jason718 Loading…
@jason718
18
Add profiling callbacks and fix logger init ordering
#689 opened May 27, 2026 by AkshitaB Contributor Loading…
9
Add MultiGroupDistributedDataParallel
#688 opened May 27, 2026 by AkshitaB Contributor • Draft
Configure attention and feed-forward norms independently
#687 opened May 27, 2026 by AkshitaB Contributor Loading…
8
Add Qwen3.5 model support (0.8B, 4B, 9B, 27B)
#684 opened May 21, 2026 by mnoukhov Loading…
4 tasks done
Add OutputDiscardCheckpoint
#682 opened May 16, 2026 by AkshitaB Contributor • Draft
5 tasks done
11
Add conversion overrides for Llama, Qwen3, and Gemma 4 models so they roundtrip properly
#677 opened May 13, 2026 by finbarrtimbers Collaborator Loading…
4
[DRAFT] Modify CosWithWarmupAndLinearDecay tail-handoff and missing super().__post_init__()
#676 opened May 12, 2026 by AkshitaB Contributor • Draft
2 of 3 tasks
Fix NaN loss when all labels on a rank are label_ignore_index
#657 opened Apr 10, 2026 by Suanmd Loading…
4 of 5 tasks
Fix LR schedulers when warmup/decay rounds to zero
#655 opened Apr 9, 2026 by xsinxx Loading…
Use metadata-backed document boundaries for SFT datasets
#653 opened Apr 2, 2026 by taivu1998 Contributor Loading…
1
1
Fix race condition in SamplingInstanceSource index cache
#651 opened Mar 27, 2026 by IanMagnusson • Draft
1 task done
Kylel/ladder yaml mix
#646 opened Mar 24, 2026 by kyleclo Contributor • Draft
Prepare release v2.5.0
#643 opened Mar 21, 2026 by tyler-romero Contributor Loading…
2 tasks
Adds option to disable post train permanent checkpoint
#631 opened Mar 4, 2026 by epwalsh Contributor Loading…
Fix: respect -t/--tokenizer CLI flag over sibling tokenizer/ directory
#629 opened Mar 3, 2026 by mario-sanz Loading…
1
3
LC Anneal
#626 opened Feb 26, 2026 by dirkgr Contributor Loading…
6
mixtures from yamls
#615 opened Feb 21, 2026 by epwalsh Contributor Loading…
2
Add ReduceType.weighted_mean for weighted metric reduction
#604 opened Feb 11, 2026 by finbarrtimbers Collaborator Loading…
3 tasks done
2
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.