Lists (8)
Stars
An Extensible Continual Learning Framework Focused on Language Models (LMs)
Long Range Arena for Benchmarking Efficient Transformers
Structured state space sequence models
[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models
High-Resolution Image Synthesis with Latent Diffusion Models
Graphormer is a general-purpose deep learning backbone for molecular modeling.
The official implementation of Diffusion-KTO: Aligning Diffusion Models by Optimizing Human Utility
Recipe for a General, Powerful, Scalable Graph Transformer
A Library for Dynamic Graph Learning (NeurIPS 2023)
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
Official inference repo for FLUX.1 models
Machine learning metrics for distributed, scalable PyTorch applications.
[ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy
Making large AI models cheaper, faster and more accessible
Ongoing research training transformer models at scale
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Generative Models by Stability AI
🚀 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
Hackable and optimized Transformers building blocks, supporting a composable construction.
🤖 Machine Learning Summer School Guide
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
Accessible large language models via k-bit quantization for PyTorch.
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
tensorboard for pytorch (and chainer, mxnet, numpy, ...)
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
A concise but complete full-attention transformer with a set of promising experimental features from various papers