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.

InternVideo2-CLIP fine-tuning (TAO video_clip) v1.0.0

Use this resource to fine-tune and deploy InternVideo2-CLIP for video-text retrieval with TAO

New

  • 379 downloads
  • 143 likes
  • 192 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install internvideo2-clip-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 LoRA training, evaluation, inference, export and TensorRT engine steps from datasets in the vadr1_chunks format. You get configuration specs and commands to validate on your image.

Mostly picked by

Updated November 2, 2026

Card for the “InternVideo2-CLIP fine-tuning (TAO video_clip)” 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.yaml: export spec
  • references/spec_template_gen_trt_engine.yaml: TensorRT engine generation

Good fit for

  • You want to adapt InternVideo2-CLIP to your video clips and texts
  • You must build a TensorRT engine for video-text retrieval

Not for

    Tags

    • internvideo2
    • video-text
    • clip
    • tao

    About

    You say

    “Fine-tune InternVideo2-CLIP on my vadr1 chunks and export the model for TensorRT.”

    Card for the “InternVideo2-CLIP fine-tuning (TAO video_clip)” 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 and deploy InternVideo2-CLIP for video-text retrieval with TAO
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md7.6 KB
    • config/skillspector-baseline.yaml1.5 KB
    • eval.config9.8 KB
    • evals/evals.json4.8 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/skill_info.yaml2.7 KB
    • references/spec_template_deploy_evaluate.yaml0.4 KB
    • references/spec_template_deploy_inference.yaml0.4 KB
    • references/spec_template_evaluate.yaml1.2 KB
    • references/spec_template_export.yaml0.8 KB
    • references/spec_template_gen_trt_engine.yaml0.4 KB
    • references/spec_template_inference.yaml1.3 KB
    • references/spec_template_train.yaml1.8 KB
    • references/tao-deploy-video-clip.md4.1 KB
    • references/tao-deploy-video-clip.skill_info.yaml2.8 KB
    • skill-card.md4.3 KB
    • SKILL.md13.9 KB
    • skill.oms.sig7.5 KB

    Origin and licence

    Listed unmodified

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

    Notice

    « tao-finetune-video-clip » (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.