Hugging Face Skills

Master HuggingFace datasets library — loading from Hub, local files, and APIs, with filtering, mapping, tokenization, and streaming for efficient data processing pipelines.

Fine-tune HuggingFace models efficiently using PEFT and LoRA — dataset preparation, training configuration, adapter merging, and model publishing for domain-specific AI.

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.

Create and manage datasets on Hugging Face Hub.

Add and manage evaluation results in Hugging Face model cards.

Gradio is a Python library for building interactive web UIs and ML demos. This skill covers the core API, patterns, and examples.

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub.

This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure.

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure.

Publish and manage research papers on Hugging Face Hub.

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help.

Trackio is an experiment tracking library for logging and visualizing ML training metrics. It syncs to Hugging Face Spaces for real-time monitoring dashboards.

Transformers.js enables running state-of-the-art machine learning models directly in JavaScript, both in browsers and Node.

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs.

Integrate HuggingFace's Inference API into your applications — serverless model inference, streaming responses, and dedicated endpoints without managing infrastructure.