Stars
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A feature-rich command-line audio/video downloader
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Extremely fast Query Engine for DataFrames, written in Rust
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Questions to ask the company during your interview
Fully open reproduction of DeepSeek-R1
Latex code for making neural networks diagrams
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…
SGLang is a high-performance serving framework for large language models and multimodal models.
Typer, build great CLIs. Easy to code. Based on Python type hints.
A collection of resources and papers on Diffusion Models
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Large Language Model Text Generation Inference
Hackable and optimized Transformers building blocks, supporting a composable construction.
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
Out-of-Core hybrid Apache Arrow/NumPy DataFrame for Python, ML, visualization and exploration of big tabular data at a billion rows per second 🚀
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image genera…
A course on aligning smol models.
Google AI 2018 BERT pytorch implementation
A natural language modeling framework based on PyTorch
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.