agentleFS
Sign inStart free
allenaiallenai/open-instruct/.claude/skills/run-all-dpo/SKILL.md

run-all-dpo

Skill3.9k starsChanged 3 days agoApache-2.0View on GitHub

Run the single-GPU then multi-node DPO debug scripts on Beaker, fix failures, and add the runs to the PR body. Use when asked to run the DPO debug scripts.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Commit all changes, then launch each of these with ./scripts/train/build_image_and_launch.sh <script>, in order:

    line 6
  2. Distinctive:

    Wait for the first to succeed before launching the second.

    line 11
  3. Distinctive:

    If they both pass, then update the PR with links to them in this format:

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Commit all changes, then launch each of these with ./scripts/train/build_image_and_launch.sh <script>, in order:

  1. scripts/train/debug/dpo/single_gpu.sh
  2. scripts/train/debug/dpo/multi_node.sh

Wait for the first to succeed before launching the second. Monitor the results and fix any errors. Only launch the multi-node experiment once single GPU has passed (exit code 0).

If they both pass, then update the PR with links to them in this format:

Runs:

  1. Single GPU DPO: Beaker
  2. Multi-node DPO: Beaker

Download now (ZIP)

Trending

More talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 1 mentionFeb 2026: 4 mentionsMar 2026: 0 mentionsApr 2026: 1 mentionMay 2026: 2 mentionsJun 2026: 0 mentionsJul 2026: 1 mentionAug 2026: 1 mentionSep 2026: 1 mentionOct 2026: 5 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the allenai/open-instruct repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about allenai/open-instruct

The biggest 5 of 57 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 57

Talked about on GitHub, Bluesky and Hacker News (57 times).

On GitHub · 50

45 more on GitHub

On Bluesky · 6

1 more on Bluesky

On Hacker News · 1

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free