Stars
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
PyTorch Tutorial for Deep Learning Researchers
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep lear…
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials,…
Data validation using Python type hints
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Fast and memory-efficient exact attention
A TTS model capable of generating ultra-realistic dialogue in one pass.
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
SQL databases in Python, designed for simplicity, compatibility, and robustness.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Open source code for AlphaFold 2.
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
🚀 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
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
💨 Fast, Async-ready, Openapi, type hints based framework for building APIs
A PyTorch implementation of EfficientNet
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
Model parallel transformers in JAX and Haiku
CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.
Denoising Diffusion Probabilistic Models
Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun
XLeRobot: Practical Dual-Arm Mobile Home Robot for $660
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Learning to Learn in TensorFlow
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)