@huggingface

hugging-face-model-trainer enables cloud-based language model fine-tuning via TRL on Hugging Face Jobs, supporting SFT, DPO, GRPO, and reward modeling with automatic Hub persistence and real-time monitoring.

fine-tunes computer vision models (detection, classification, segmentation) on hugging face's managed gpu infrastructure with results persisted to the hub. covers d-fine, rt-detr, detr, yolos, timm classifiers, and sam/sam2.

hugging-face-evaluation covers adding and managing eval results to model cards via table extraction, artificial analysis imports, and custom evaluations. integrates with hf ecosystem tools including lighteval and inspect-ai frameworks.

huggingface-papers fetches and reads research papers from hugging face and arxiv, returning markdown content or structured metadata like authors, linked models, datasets, and github repos via api.

hf-cli is a command reference for the hugging face hub cli tool covering download, upload, sync, and copy operations on models, datasets, and spaces. lacks procedural depth and actionable guidance.

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between…

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation,…

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or…

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet…

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. This is especially useful…

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset…

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating…

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO,…

huggingface-gradio — an installable skill for AI agents, published by huggingface/skills.