tao-port-huggingface-model

Name: tao-port-huggingface-model
Availability: InStock
Author: NVIDIA TAO

Integrate HuggingFace Computer Vision models into the NVIDIA TAO Toolkit.

83|20|Updated Apr 16, 2026

Search Tags:#deployment #integration #computer vision #huggingface #nvidia tao toolkit

Ready to run

npx skills add https://github.com/NVIDIA-TAO/tao-skill-bank --skill tao-port-huggingface-model

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tao-port-huggingface-model
Source: https://github.com/NVIDIA-TAO/tao-skill-bank/tree/main/skills/applications/tao-port-huggingface-model
Command: npx skills add https://github.com/NVIDIA-TAO/tao-skill-bank --skill tao-port-huggingface-model

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, nvidia driver, cuda, docker, ngc api key, hf_token, tao toolkit, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill simplifies the process of integrating HuggingFace Computer Vision models into the NVIDIA TAO Toolkit, allowing for easy configuration, training, and deployment.

Core Features & Use Cases

Model Integration: Seamlessly integrate HuggingFace models with the TAO Toolkit.
Full Workflow Support: Covers the entire process from prerequisites check to optimization and tuning.
Use Case: For a developer who wants to integrate a HuggingFace model into the TAO Toolkit for training, ONNX export, and TensorRT deployment, this Skill provides a comprehensive solution.

Quick Start

Run the skill with the HuggingFace model URL or ID: tao-port-huggingface-model <model_url_or_id>

Frequently Asked Questions about tao-port-huggingface-model

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I integrate a HuggingFace computer vision model into the NVIDIA TAO Toolkit?▼

To integrate a HuggingFace computer vision model into the NVIDIA TAO Toolkit, you can run this Skill with your model URL or ID to configure it for training and TensorRT deployment.

What computer vision tasks are supported when porting HuggingFace models to TAO Toolkit?▼

Porting HuggingFace models to the TAO Toolkit supports classification, detection, segmentation, zero-shot detection, and depth estimation tasks for full model training and optimization.

Do I need an NGC API key and CUDA to deploy HuggingFace models with TAO Toolkit?▼

Yes, deploying HuggingFace models with the TAO Toolkit requires an NGC API key, an HF_TOKEN, Python 3.10+, NVIDIA driver, CUDA 13.0+, Docker, and the nvidia-container-toolkit.

Can I export HuggingFace models to ONNX and TensorRT using the TAO Toolkit?▼

Yes, you can export HuggingFace models to ONNX and TensorRT using the TAO Toolkit, which supports the full workflow from model integration and training to final deployment optimization.

What's the best way to optimize HuggingFace models for TensorRT deployment?▼

The best way to optimize HuggingFace models for TensorRT deployment is using this Skill to integrate them into the TAO Toolkit ecosystem, enabling full training, ONNX export, and optimization.