Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Cosmos-Embed1 fine-tuning for video-text retrieval v1.0.0

Use this resource to fine-tune Cosmos-Embed1 and produce video-text embeddings with TAO

New

  • 399 downloads
  • 169 likes
  • 128 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install cosmos-embed-video-text-finetuning

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent prepares the training, evaluation, inference and HF or ONNX export specs, and explains the data and weight formats. You get embeddings to search or deduplicate videos.

Mostly picked by

Updated November 2, 2026

Card for the “Cosmos-Embed1 fine-tuning for video-text retrieval” skill

Details

Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • references/spec_template_train.yaml: training spec
  • references/spec_template_export_onnx.yaml: ONNX export
  • references/skill_info.yaml: container and action information

Good fit for

  • You want to search videos with a sentence
  • You must semantically deduplicate video clips

Not for

    Tags

    • cosmos-embed
    • video
    • search
    • embeddings

    About

    You say

    “Find the videos in my corpus that match “a forklift in a warehouse”.”

    Card for the “Cosmos-Embed1 fine-tuning for video-text retrieval” skill

    Skill published by nvidia under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to fine-tune Cosmos-Embed1 and produce video-text embeddings with TAO
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md7.1 KB
    • config/skillspector-baseline.yaml1 KB
    • evals/evals.json0.8 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/skill_info.yaml2.9 KB
    • references/spec_template_evaluate.yaml1.2 KB
    • references/spec_template_export_hf.yaml0.8 KB
    • references/spec_template_export_onnx.yaml0.8 KB
    • references/spec_template_inference.yaml1.2 KB
    • references/spec_template_train.yaml2.3 KB
    • skill-card.md4.4 KB
    • SKILL.md15.3 KB
    • skill.oms.sig6.2 KB

    Origin and licence

    Listed unmodified

    Author
    nvidia
    Source
    github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/tao-finetune-cosmos-embed
    Licence
    Apache-2.0

    Notice

    « tao-finetune-cosmos-embed » (nvidia, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.