Hugging Face Skills

huggingface

transformers-js is a JavaScript library for running machine learning models, supporting NLP, computer vision, and audio tasks with pre-trained models from Hugging Face Hub.

huggingface

This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens

huggingface

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. Covers SFT, DPO, GRPO and reward mod

huggingface

huggingface-paper-publisher is a skill that enables AI researchers to publish and manage research papers on Hugging Face Hub, supporting paper creation, model/dataset linking, and authorship management.

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. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.

huggingface

huggingface-papers is a skill that enables users to access and summarize AI research papers from Hugging Face and arXiv.

huggingface

huggingface-trackio is a Python library for logging and visualizing ML training metrics, supporting real-time dashboard visualization and alerts.

huggingface

huggingface-community-evals is a skill for running local evaluations of Hugging Face models using inspect-ai and lighteval.

huggingface

huggingface-gradio is a Python library for building interactive web UIs and ML demos, allowing developers to create custom Gradio apps and chatbots with ease.

huggingface

huggingface-datasets is a skill for executing Hugging Face Dataset Viewer API workflows, enabling dataset exploration and extraction capabilities.

huggingface

hf-cli is a command-line tool for interacting with the Hugging Face Hub, providing a seamless way to manage models, datasets, and Spaces.

huggingface

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.