902 dependents
| Package | Description | Downloads/month |
|---|---|---|
| 🤗 Transformers: the model-definition framework for state-of-the-art machine lear... | 141.8M | |
| 🚀 A simple way to launch, train, and use PyTorch models on almost any device and... | 24.8M | |
| The largest collection of PyTorch image encoders / backbones. Including train, e... | 13.2M | |
| 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. | 10.8M | |
| 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio gener... | 8.2M | |
| An open source implementation of CLIP. | 3.1M | |
| This package contains the AI models used by the Docling PDF conversion package | 2.4M | |
| State-of-the-art speaker diarization toolkit | 2.2M | |
| Give your project support for a variety of PyTorch model architectures, includin... | 1.8M | |
| PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial P... | 1.7M | |
| Semantic segmentation models with 500+ pretrained convolutional and transformer-... | 704K | |
| Fast State-of-the-Art Static Embeddings | 491K | |
| Neural Network Compression Framework for enhanced OpenVINO™ inference | 456K | |
| PyTorch native post-training library | 405K | |
| A unified library of SOTA model optimization techniques like quantization, pruni... | 376K | |
| 💬 Open source machine learning framework to automate text- and voice-based con... | 314K | |
| A pytorch quantization backend for optimum | 267K | |
| Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, ... | 171K | |
| This is an open-source version of the representation engineering framework for s... | 167K | |
| A toolset for compressing, deploying and serving LLM | 123K | |
| Memory Management for the GPU Poor | 123K | |
| VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice D... | 122K | |
| Supercharge Your LLM with the Fastest KV Cache Layer | 120K | |
| Generative models for conditional audio generation | 118K | |
| Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech wi... | 104K | |
| Real-time avatar engine — 100+ FPS on CPU. Generate lip-synced video, stream liv... | 104K | |
| SoTA open-source TTS | 98K | |
| Training Sparse Autoencoders on Language Models | 92K | |
| Invoke is a leading creative engine for Stable Diffusion models, empowering prof... | 77K | |
| Named Tensors for Legible Deep Learning in JAX | 75K | |
| An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ ... | 75K | |
| Post-training with Tinker | 73K | |
| PyTorch building blocks for the OLMo ecosystem | 71K | |
| sdkit (stable diffusion kit) is an easy-to-use library for using Stable Diffusio... | 67K | |
| 💡 All-in-one AI framework for semantic search, LLM orchestration and language mo... | 46K | |
| The WeightWatcher tool for predicting the accuracy of Deep Neural Networks | 44K | |
| Support PyTorch model conversion with LiteRT. | 43K | |
| Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defe... | 41K | |
| MLX native implementations of state-of-the-art generative image models | 40K | |
| Efficiently run models quantized with SPQR | 40K | |
| LLM model quantization (compression) toolkit with HW acceleration support for Nv... | 38K | |
| Things you can do with the token embeddings of an LLM | 38K | |
| A flexible, adaptive classification system for dynamic text classification | 37K | |
| Easy-to-use and powerful LLM and SLM library with awesome model zoo. | 36K | |
| Unified automatic quality assessment for speech, music, and sound. | 36K | |
| Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax | 34K | |
| Kyutai's pocket-sized text-to-speech! | 34K | |
| Inference code for "TabDPT: Scaling Tabular Foundation Models on Real Data" | 33K | |
| Influence Functions with (Eigenvalue-corrected) Kronecker-factored Approximate C... | 31K | |
| Python Package for Airborne RGB machine learning | 30K |
