cosmos3-qwen3-vl-robovqa-sft SKILL.md skillA
cosmos3-qwen3-vl-robovqa-sft from nvidia/cosmos-framework is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nvidia/cosmos-framework/cosmos3-qwen3-vl-robovqa-sft@git:20261031.50e8834Pins git:20261031.50e8834 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nvidia/cosmos-framework
- Path
.agents/skills/cosmos3-qwen3-vl-robovqa-sft/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261031.50e8834, committed Oct 31, 2026
- Size
- 17,378 bytes
- Repository stars
- 613
- License
- a license file GitHub does not identify
Fine-tune Qwen3-VL-8B-Instruct, a vision-language model from outside the Cosmos family, with the Cosmos Framework posttrain SFT path on robot-video question answering (RoboVQA), on one GPU, and score it before and after with the same evaluator. Use when the user asks to "fine-tune Qwen3-VL with Cosmos Framework", "train a non-Cosmos model or a VLM in the framework", "run SFT on robot videos / RoboVQA", "reproduce the Qwen3-VL RoboVQA result", or wants a worked post-training example with a…
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
# Qwen3-VL-8B SFT on RoboVQA (one GPU) One job: full-parameter SFT of `Qwen/Qwen3-VL-8B-Instruct` on the RoboVQA training clips through the framework's posttrain SFT path, then the same scorer on 1,000 held-out clips before and after. Example from the held-out set: "put the box on the table Q: possible right now?", reference `no`: the base model answers `yes`, the fine-tuned model `no`. Measured on one NVIDIA GB300 (aarch64, driver 595, CUDA 13.0), two runs at seed 0 (training is not bit-reproducible): exact match 0.548 before, 0.632 and 0.620 after. Details: [`references/measured-run.md`](references/measured-run.md). ## For an agent The whole job is the eight steps below, run in order, each one command. A request that fits in one line: > Using the `cosmos3-qwen3-vl-robovqa-sft` skill in this Cosmos Framework checkout: set up the environment, > download the model and RoboVQA, prepare the training rows, run the preflight, score Qwen3-VL-8B before > training, fine-tune for one epoch, export, and score after. Report both scores. Rules: run the steps in the order listed; after each step compare the last lines with the step's "Expected"; …
Read the whole file at its exact version.
How to install
mdr add nvidia/cosmos-framework/cosmos3-qwen3-vl-robovqa-sft@sha256:94203a43fe64da11The line at the top of this page pins the label git:20261031.50e8834, 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_gjaax5tonrrumbjv)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 31, 2026.
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 (17378 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
nvidia/cosmos-framework · 613 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gjaax5tonrrumbjv GET https://markdownregistry.com/api/v1/resolve?ref=nvidia/cosmos-framework/cosmos3-qwen3-vl-robovqa-sft GET https://markdownregistry.com/api/v1/blob/94203a43fe64da11b3840434e474d79c21f7cf88268f9c250ebab74614a89649
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.