3,031 dependents
| Package | Description | Downloads/month |
|---|---|---|
| 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production | 160.3M | |
| 🤗 Transformers: the model-definition framework for state-of-the-art machine lear... | 141.8M | |
| 🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use ... | 116.3M | |
| State-of-the-Art Text Embeddings | 25.7M | |
| 🚀 A simple way to launch, train, and use PyTorch models on almost any device and... | 24.8M | |
| Build and share delightful machine learning apps, all in Python. 🌟 Star to suppo... | 16.2M | |
| The largest collection of PyTorch image encoders / backbones. Including train, e... | 13.2M | |
| Fast, Accurate, Lightweight Python library to make State of the Art Embedding | 11.6M | |
| 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. | 10.8M | |
| Build and share delightful machine learning apps, all in Python. 🌟 Star to suppo... | 9.7M | |
| 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio gener... | 8.2M | |
| Faster Whisper transcription with CTranslate2 | 7.4M | |
| An open source implementation of CLIP. | 3.1M | |
| This package contains the AI models used by the Docling PDF conversion package | 2.4M | |
| A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face ... | 2.4M | |
| State-of-the-art speaker diarization toolkit | 2.2M | |
| Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt... | 1.9M | |
| 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sente... | 1.7M | |
| The agent engineering platform | 1.6M | |
| All-in-one speech toolkit in pure Python and Pytorch | 1.6M | |
| Low-code development tool based on PaddlePaddle. | 1.6M | |
| Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt... | 1.4M | |
| A library for performing inference using trained models. | 1.1M | |
| WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarizatio... | 1.1M | |
| A DataSource for reading and writing HuggingFace Datasets in Spark | 1M | |
| aider is AI pair programming in your terminal | 864K | |
| A scalable generative AI framework built for researchers and developers working ... | 798K | |
| Semantic segmentation models with 500+ pretrained convolutional and transformer-... | 704K | |
| The simplest way to serve AI/ML models in production | 632K | |
| ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It... | 629K | |
| Download compute kernels | 622K | |
| 🤗 smolagents: a barebones library for agents. Agents write python code to call t... | 587K | |
| Generalist and Lightweight Model for Named Entity Recognition (Extract any entit... | 556K | |
| llama-index embeddings huggingface integration | 523K | |
| 🤖 A PyTorch library of curated Transformer models and their composable component... | 521K | |
| A file utility for accessing both local and remote files through a unified inter... | 518K | |
| Python Toolkit for Causal and Probabilistic Reasoning | 448K | |
| Lepton AI Platform | 447K | |
| PyTorch native post-training library | 405K | |
| Auxillary models for controlnet | 354K | |
| Packaged version of ultralytics/yolov5 + many extra features | 332K | |
| A unified framework for reinforcement learning environments | 327K | |
| https://hf.co/hexgrad/Kokoro-82M | 312K | |
| docTR (Document Text Recognition) - a seamless, high-performing & accessible lib... | 287K | |
| AIPerf is a package for performance testing of AI models | 285K | |
| Transforms complex documents like PDFs and Office docs into LLM-ready markdown/J... | 282K | |
| The Argilla python server SDK | 277K | |
| A Neural Framework for MT Evaluation | 272K | |
| FAIR Chemistry's library of machine learning methods for chemistry | 272K | |
| Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls) | 270K |
