Hugging Face Transformers
Natural Language Processing & Language Models
The reference library for pretrained transformer models in text, vision and audio, with thousands of models on the Hugging Face Hub.
AI Frameworks & Libraries Encyclopedia
Discover the most important frameworks and libraries used to build and develop AI systems, and learn how to use them through explanations, examples and applied projects.
Natural Language Processing & Language Models
The reference library for pretrained transformer models in text, vision and audio, with thousands of models on the Hugging Face Hub.
Natural Language Processing & Language Models
A framework for building language model applications: connecting models to tools, documents and memory, and building agents and RAG chains.
Computer Vision & Image Processing
An open-source framework built on PyTorch for deep learning in medical imaging: loading medical images, their transforms, networks and metrics.
Scientific Computing & Data Processing Libraries
The fundamental library for multidimensional arrays and numerical computing in Python, on which most data science and AI libraries are built.
Quantum Machine Learning
A framework for differentiable quantum programming that connects quantum circuits to PyTorch, JAX and TensorFlow and works with many hardware backends and simulators.
Deep Learning Frameworks
An open-source deep learning framework based on dynamic computation graphs and automatic differentiation, and the most used in scientific research.
Machine Learning Frameworks & Libraries
The reference library for classical machine learning in Python: classification, regression, clustering, dimensionality reduction and evaluation through a unified API.
Interpretability & Explainable AI
An explanation library based on Shapley values from game theory to estimate each feature's contribution to a model's prediction, locally and globally.
Deep Learning Frameworks
A comprehensive machine learning platform from Google for building, training and deploying models on servers, phones and browsers.
An open-source compiler for machine learning models that optimises them and generates fast code for many kinds of hardware.
A just-in-time (JIT) compiler that turns numerical Python functions into fast machine code with a single decorator, with support for parallelism and CUDA kernels.
A language and compiler for writing high-performance GPU kernels in a Python-like language without writing CUDA directly, used by PyTorch in torch…
NVIDIA's suite of libraries for accelerating data science on GPUs: cuDF for tables, cuML for machine learning and cuGraph for graphs.
An array library compatible with the NumPy and SciPy APIs that runs on NVIDIA and AMD GPUs.
NVIDIA's platform for parallel computing on its GPUs, on which most deep learning frameworks rely for acceleration.
Source: PyPI, checked on 21 November 2026
Source: PyPI, checked on 21 November 2026
Source: PyPI, checked on 21 November 2026
Source: PyPI, checked on 21 November 2026
Source: PyPI, checked on 21 November 2026
Source: PyPI, checked on 21 November 2026
Describe your project or the problem you are working on, and the AI assistant will suggest suitable libraries from the encyclopedia, explaining why it chose them, with learning and application links.
Sections
No section has this name. Press “Search” to search all site content.
Favourites
My results & certificates
My academy progressMy quiz resultsKids’ progressAcademy certificatesQuiz certificatesStart any lesson or quiz and it will show up here so you can get back to it quickly.
Settings
I am the AI Frameworks & Libraries Assistant. Describe your project or ask me about a library, a comparison or a code example, and I will answer from the encyclopedia's database with links and sources.
Answers from the encyclopedia's database only, without a language model and without sending your question to any third party.
The assistant can make mistakes, so check the attached sources.