lucidrains / lion-pytorch
π¦ Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
β2,128Updated 5 months ago
Alternatives and similar repositories for lion-pytorch:
Users that are interested in lion-pytorch are comparing it to the libraries listed below
- A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.β2,574Updated 2 months ago
- Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Modelsβ789Updated 10 months ago
- Machine learning metrics for distributed, scalable PyTorch applications.β2,258Updated this week
- Tensors, for human consumptionβ1,247Updated 5 months ago
- FFCV: Fast Forward Computer Vision (and other ML workloads!)β2,924Updated 10 months ago
- maximal update parametrization (Β΅P)β1,500Updated 9 months ago
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch modelβ577Updated 5 months ago
- D-Adaptation for SGD, Adam and AdaGradβ521Updated 3 months ago
- Foundation Architecture for (M)LLMsβ3,074Updated last year
- Schedule-Free Optimization in PyTorchβ2,150Updated 3 weeks ago
- SAM: Sharpness-Aware Minimization (PyTorch)β1,867Updated last year
- Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.β2,837Updated last month
- View model summaries in PyTorch!β2,771Updated last week
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorchβ672Updated 5 months ago
- Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.β1,429Updated this week
- Structured state space sequence modelsβ2,620Updated 9 months ago
- Implementation of Perceiver, General Perception with Iterative Attention, in Pytorchβ1,138Updated last year
- Pytorch library for fast transformer implementationsβ1,701Updated 2 years ago
- Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022β1,115Updated 11 months ago
- torchview: visualize pytorch modelsβ914Updated last week
- The official implementation of βSophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-trainingββ957Updated last year
- A concise but complete full-attention transformer with a set of promising experimental features from various papersβ5,288Updated last week
- functorch is JAX-like composable function transforms for PyTorch.β1,424Updated this week
- Implementation of ConvMixer for "Patches Are All You Need? π€·"β1,071Updated 2 years ago
- Vector (and Scalar) Quantization, in Pytorchβ3,195Updated this week
- Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.β1,822Updated 4 months ago
- torch-optimizer -- collection of optimizers for Pytorchβ3,107Updated last year
- Transformer based on a variant of attention that is linear complexity in respect to sequence lengthβ763Updated last year
- solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightningβ1,481Updated last week
- Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)β1,905Updated 9 months ago