OLMo-core
CLAUDE.md1.8k starsChanged 9 months agoApache-2.0View on GitHub
See @AGENTS.md
3 other projects use a version of this.
Trending
Steady talk.about the whole repository
Most recently taken up by
- nlothian/Vibe-Prologword for word, first seen Oct 9, 2026
- percona/percona-xtradb-cluster-operatorword for word, first seen Oct 9, 2026
- DataDog/dd-trace-dotnetword for word, first seen Oct 8, 2026
Who's talking about allenai/OLMo-core
- @ai2.bsky.social“For pretraining, we created a new trainer called OLMo-core! v2 landed today, and it is a significant …”Bluesky · Mar 13, 2025 · 4 likes
- NVIDIA/Megatron-LM“[BUG] MoE router can potentially hack the aux loss when using sigmoid gating function”GitHub · Apr 17, 2025 · 3 reactions
- allenai/open-instruct“Stop the forced ephemeral_save_interval default rejecting small checkpoint intervals”GitHub · Aug 10, 2026 · 1 reactions
- AkihikoWatanabe/paper_notes“Olmo-core: Building blocks for OLMo modeling and training, AI2, 2024.06”GitHub · Oct 2, 2026
- allenai/EMO“Extension for SFT”GitHub · Apr 3, 2026
The biggest 5 of 20 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 20
Talked about on GitHub and Bluesky (20 times).
On GitHub · 19
- Apr 17, 2025[BUG] MoE router can potentially hack the aux loss when using sigmoid gating function — NVIDIA/Megatron-LM3 reactions · 8 comments
- Aug 10, 2026Stop the forced ephemeral_save_interval default rejecting small checkpoint intervals — allenai/open-instruct1 reaction · 3 comments
- Oct 2, 2026Olmo-core: Building blocks for OLMo modeling and training, AI2, 2024.06 — AkihikoWatanabe/paper_notes0 reactions · 2 comments
- Apr 3, 2026Extension for SFT — allenai/EMO0 reactions
- Mar 14, 2026Configurable Z Loss — pytorch/torchtitan0 reactions
14 more on GitHub
- Mar 11, 2026Dockerfile modification — allenai/molmoact0 reactions · 1 comment
- Sep 18, 2025Make work_dir/dataset_cache not point to a url on Augusta — allenai/olmo-cookbook0 reactions
- Jun 9, 2025unshard.py trys to import a non-existing method in olmo-core — allenai/OLMo0 reactions · 4 comments
- Jun 5, 2025add bos token if in tokenizer — allenai/OLMo-in-loop-evals0 reactions
- May 2, 2025Draft updates for beaker-py v2 — allenai/olmo-cookbook0 reactions · 2 comments
- Apr 11, 2025use latest olmo-core ladder for how batch size and LR are computed for different sequence lengths — allenai/regmixer0 reactions
- Apr 11, 2025use updated in loop downstream evaluators — allenai/regmixer0 reactions
- Apr 2, 2025OLMo in-loop evals change with `torch.compile()` in 2.7.0 — pytorch/pytorch0 reactions · 11 comments
- Mar 6, 2025Make min patch size configurable — allenai/olmoearth_pretrain0 reactions
- Feb 14, 2025love2code (3B) recipe — allenai/olmo-cookbook0 reactions
- Jan 27, 2025Set up Beaker runs — allenai/olmoearth_pretrain0 reactions
- Jul 11, 2024Cannot convert internal OLMo checkpoint to HF — allenai/OLMo0 reactions · 2 comments
- Jun 25, 2024Tokenizer with relative path import fails when using olmo as pip library — allenai/OLMo0 reactions
- May 5, 2024Increment torch version — allenai/OLMo0 reactions · 3 comments
On Bluesky · 1
- Mar 13, 2025For pretraining, we created a new trainer called OLMo-core! v2 landed today, and it is a significant improvement over our previous library:… — @ai2.bsky.social4 likes and reposts · 2 replies
Other versions3 projects use a version of this.
Word for word · 3
- percona/percona-xtradb-cluster-operator★ 625100% same
- DataDog/dd-trace-dotnet★ 572100% same
- nlothian/Vibe-Prolog★ 56100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- AGENTS.mdAGENTS.md
- training-smoke-testSkill
The file
Files
See @AGENTS.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.