lucidrains / lion-pytorchLinks
π¦ Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
β2,166Updated 10 months ago
Alternatives and similar repositories for lion-pytorch
Users that are interested in lion-pytorch are comparing it to the libraries listed below
Sorting:
- maximal update parametrization (Β΅P)β1,611Updated last year
- Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Modelsβ799Updated 4 months ago
- The official implementation of βSophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-trainingββ976Updated last year
- Foundation Architecture for (M)LLMsβ3,119Updated last year
- Machine learning metrics for distributed, scalable PyTorch applications.β2,342Updated this week
- Schedule-Free Optimization in PyTorchβ2,224Updated 5 months ago
- D-Adaptation for SGD, Adam and AdaGradβ524Updated 9 months ago
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorchβ766Updated 2 months ago
- β785Updated last month
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch modelβ616Updated 10 months ago
- SAM: Sharpness-Aware Minimization (PyTorch)β1,925Updated last year
- Tensors, for human consumptionβ1,316Updated 2 weeks ago
- torchview: visualize pytorch modelsβ996Updated 5 months ago
- TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.β1,656Updated this week
- A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.β2,851Updated 4 months ago
- Cramming the training of a (BERT-type) language model into limited compute.β1,348Updated last year
- An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"β1,203Updated 2 years ago
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.β479Updated 2 years ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence lengthβ801Updated last year
- A concise but complete full-attention transformer with a set of promising experimental features from various papersβ5,633Updated this week
- Structured state space sequence modelsβ2,750Updated last year
- Implementation of ConvMixer for "Patches Are All You Need? π€·"β1,077Updated 2 years ago
- Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022β1,146Updated last year
- Vector (and Scalar) Quantization, in Pytorchβ3,622Updated last week
- Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.β3,182Updated 5 months ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)β1,288Updated 10 months ago
- Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)β1,956Updated last year
- View model summaries in PyTorch!β2,868Updated last week
- Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagationβ1,487Updated 2 years ago
- Implementation of Perceiver, General Perception with Iterative Attention, in Pytorchβ1,171Updated 2 years ago