oumi-weights-lab SKILL.md skillA
oumi-weights-lab from oumi-ai/weights-lab is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add oumi-ai/weights-lab/oumi-weights-lab@git:20261107.5bd03b0Pins git:20261107.5bd03b0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- oumi-ai/weights-lab
- Path
skills/oumi-weights-lab/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261107.5bd03b0, committed Nov 7, 2026
- First version recorded
- Nov 7, 2026
- Size
- 17,459 bytes
- Repository stars
- 5
- License
- Apache-2.0
Use when asked to find out how an open-weights language model does something (which heads, MLPs, neurons, features, or directions carry a behavior) or to test such a claim; when asked to ablate, zero, edit, swap, or compare a model's parameters, including LoRA adapters; when measuring how a weight change affects a model's answers; or when recording, patching, or probing a Hugging Face causal model's activations or gradients.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Oumi Weights Lab
Run Python against a live model with tested calls for finding mechanisms, editing weights with exact undo, and measuring what changed. There are two ways to run it, with the same `lab` object:
- **A script**, for a model that loads in seconds, such as one under a billion parameters on CPU. Write a file that calls `open_lab` and run it with `oumi-weights-lab script analysis.py`, which runs it in the lab's own environment. A script session holds only `artifacts/`, so `send`, `peek`, `stop` and `backup` do not apply to it.
- **A persistent worker**, for a large model or a long session. Load the model once, then send Python snippets (see Session commands). Snippets share state, so an edit made in one is measured in the next, and the worker saves every snippet's source, output, and forward-pass count in the session directory.
Scripts and snippets are trusted Python with the user's filesystem and network access.
## Understand a model: start here
Don't write your own ablation loops and hooks. These calls do it, tested, and leave the model as they found it:
```python
from oumi_weights_lab import open_lab
lab = open_lab(
"/abs/path/to/model", device="cpu"
…Read the whole file at its exact version.
How to install
mdr add oumi-ai/weights-lab/oumi-weights-lab@sha256:d79b1e43158c20b8The line at the top of this page pins the label git:20261107.5bd03b0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_szg6uj6tkf3w2bbu)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, all committed on Nov 7, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261107.5bd03b0 latest | 2026-11-07 | 5bd03b0 | 17,459 B | A | view · diff |
| git:20261107.72d8eec | 2026-11-07 | 72d8eec | 14,551 B | A | view · diff |
| git:20261107.03ab8b8 | 2026-11-07 | 03ab8b8 | 14,110 B | A | view · diff |
| git:20261107.f2ad1f8 | 2026-11-07 | f2ad1f8 | 12,198 B | A | view · diff |
| git:20261107.7ec193d | 2026-11-07 | 7ec193d | 12,052 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (17459 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
oumi-ai/weights-lab · 5 stars · license Apache-2.0 · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_szg6uj6tkf3w2bbu GET https://markdownregistry.com/api/v1/resolve?ref=oumi-ai/weights-lab/oumi-weights-lab GET https://markdownregistry.com/api/v1/blob/d79b1e43158c20b856fbddf9e0af8023815c8223f37cdb40a7860c2caebee388
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.