Streamlit — A faster way to build and share data apps.

Apache Airflow - A platform to programmatically author, schedule, and monitor workflows

Open deep learning compiler stack for cpu, gpu and specialized accelerators

📈 Log and track ML metrics, parameters, models with Git and/or DVC

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

A high-throughput and memory-efficient inference and serving engine for LLMs

A TensorFlow Implementation of the Transformer: Attention Is All You Need

Production-Grade Container Scheduling and Management

a structural diff that understands syntax 🟥🟩

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

Upload video clips to a free image hosting service

⭐️ Companies that don't have a broken hiring process

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Python bindings to PDFium

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

LLM training in simple, raw C/CUDA

[NeurIPS 2024] SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challen…

🚀 List of distributed system projects for inspiration and learning to build distributed services from real world examples

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

🦁 The Leo Programming Language. A Programming Language for Formally Verified, Zero-Knowledge Applications

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Implementation of the Deep Deterministic Policy Gradient and Hindsight Experience Replay.

A project to parse klarf file and get klarf content as dataclass

Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"

Examples and guides for using the OpenAI API

Minimal and Clean Reinforcement Learning Examples

Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app

Hands-on Deep Reinforcement Learning, published by Packt

Open source codebase powering the HuggingChat app

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.