AI Agent Skills

Use Hugging Face with JavaScript

🤗 AutoTrain Advanced

This repo is the homebase of a community driven course on Computer Vision with Neural Networks. Feel free to join us on the Hugging Face discord: hf.co/join/discord

🤗🖼️ HuggingPics: Fine-tune Vision Transformers for anything using images found on the web.

🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

A blazing fast inference solution for text embeddings models

[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

Projects based on SigLIP (Zhai et. al, 2023) and Hugging Face transformers integration 🤗

Tensorflow implementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

Hyperbolic Vision Transformers: Combining Improvements in Metric Learning | Official repository

Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Codex

FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers