Hugging Face Skills

huggingface

Transformers.js permite executar modelos de aprendizado de máquina de ponta em JavaScript, tanto em navegadores quanto em ambientes Node.js, sem necessidade de servidor.

huggingface

Hugging Face Jobs é uma habilidade de agente de IA que permite executar trabalhos em nuvem para processamento de dados e treinamento de modelos

huggingface

This skill trains language models using TRL on Hugging Face infrastructure, covering SFT, DPO, GRPO, and reward modeling. It benefits developers by providing cloud GPU training and GGUF conversion for local deployment.

huggingface

O que é o huggingface-paper-publisher? É um skill que permite publicar e gerenciar artigos de pesquisa no Hugging Face Hub.

huggingface

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...

huggingface

The Hugging Face Papers skill enables developers to look up and read AI research papers in markdown, and access structured metadata such as authors and linked models. This skill benefits developers and researchers by providing easy access to AI research insights.

huggingface

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.

huggingface

This skill enables developers to test Hugging Face models locally, streamlining backend selection and model comparisons. It supports inspect-ai and lighteval for efficient evaluations.

huggingface

Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.

huggingface

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.

huggingface

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command.

huggingface

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.