🦜🔗 The platform for reliable agents.

Inference code for Llama models

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

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

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

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

Low-code framework for building custom LLMs, neural networks, and other AI models

NumPy & SciPy for GPU

Modin: Scale your Pandas workflows by changing a single line of code

Hydra is a framework for elegantly configuring complex applications

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

the portable Python dataframe library

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Adding guardrails to large language models.

🚀 Efficient implementations of state-of-the-art linear attention models

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

Download the entire Wayback Machine archive for a given URL.

FFCV: Fast Forward Computer Vision (and other ML workloads!)

Gin provides a lightweight configuration framework for Python

Benchmark datasets, data loaders, and evaluators for graph machine learning

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

A tiny library for coding with large language models.

Big & Small LLMs working together

Cython implementation of Toolz: High performance functional utilities

Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.

Explore and understand your training and validation data.

Processed / Cleaned Data for Paper Copilot