Skip to content

Pull requests: allenai/OLMo-core

New pull request New
45 Open 447 Closed
45 Open 447 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

Bottom-up flops estimation & total flops tracking
#511 opened Dec 22, 2025 by tyler-romero Loading…
MXFP8 Linear Support
#510 opened Dec 20, 2025 by tyler-romero Loading…
5
Anejs/linear rnns
#506 opened Dec 17, 2025 by tyler-romero • Draft
Add a Llama-like 7B training script for data ablations
#505 opened Dec 16, 2025 by epwalsh Loading…
1
Add DataMixtureMonitorCallback for per-source data mixture metrics
#501 opened Dec 15, 2025 by DivijChawla Loading…
Use MixedPrecision config for DDP
#489 opened Dec 1, 2025 by tyler-romero • Draft
Add --print-shape debug flag for logits shape debugging
#483 opened Nov 29, 2025 by computerologykj-maker Loading…
6
Fix MFU Calculation for SWA and GQA (Issue #475)
#480 opened Nov 26, 2025 by ada-ggf25 Loading…
1
9
2B config
#470 opened Nov 20, 2025 by dirkgr • Draft
3
[WIP] nsys profiler integration
#463 opened Nov 17, 2025 by tyler-romero • Draft
Tyler/olmoe dev v2 fork
#462 opened Nov 17, 2025 by tyler-romero • Draft
Jacobm flex olmo sft
#461 opened Nov 16, 2025 by jacob-morrison • Draft
Kevinf/gradient dumper
#438 opened Oct 30, 2025 by farhatkevin Loading…
22
[WIP] Add support for parametrizations like muP
#436 opened Oct 29, 2025 by 2015aroras • Draft
@dirkgr @epwalsh
olmo3-32b midtraining
#433 opened Oct 24, 2025 by aetting Loading…
33
Adds a gradient dumper callback, and a script that uses it.
#432 opened Oct 24, 2025 by dirkgr • Draft
Flex Attention support with sinks
#417 opened Oct 9, 2025 by aman-17 Loading…
6
Jacobm final merge sft
#400 opened Sep 30, 2025 by jacob-morrison Loading…
52
bnb style adamw implemenation (better numerical properties)
#385 opened Sep 23, 2025 by tyler-romero • Draft
3
Optionally don't load optimizer state
#367 opened Sep 11, 2025 by dirkgr Loading…
3
OLMo 2.5 1B
#358 opened Aug 30, 2025 by dirkgr Loading…
1
Add option to greedily pack documents with the padded FSL dataset
#346 opened Aug 15, 2025 by epwalsh Loading…
1
MuP partial implementation
#339 opened Aug 7, 2025 by 2015aroras • Draft
Benjaminm/tok
#336 opened Aug 5, 2025 by tyler-romero • Draft
Jacobm oi data
#325 opened Jul 16, 2025 by jacob-morrison Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.