Alternatives and similar repositories for mup:

Users that are interested in mup are comparing it to the libraries listed below

• Liuhong99 / Sophia
  The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”
  ☆957Updated last year
• JonasGeiping / cramming
  Cramming the training of a (BERT-type) language model into limited compute.
  ☆1,331Updated 10 months ago
• google / learned_optimization
  ☆776Updated last week
• lucidrains / RETRO-pytorch
  Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
  ☆864Updated last year
• pytorch / functorch
  functorch is JAX-like composable function transforms for PyTorch.
  ☆1,424Updated this week
• google-research / long-range-arena
  Long Range Arena for Benchmarking Efficient Transformers
  ☆751Updated last year
• pytorch / tensordict
  TensorDict is a pytorch dedicated tensor container.
  ☆920Updated this week
• lucidrains / lion-pytorch
  🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
  ☆2,128Updated 5 months ago
• HazyResearch / H3
  Language Modeling with the H3 State Space Model
  ☆520Updated last year
• facebookresearch / bitsandbytes
  Library for 8-bit optimizers and quantization routines.
  ☆716Updated 2 years ago
• HazyResearch / safari
  Convolutions for Sequence Modeling
  ☆878Updated 10 months ago
• facebookresearch / fairscale
  PyTorch extensions for high performance and large scale training.
  ☆3,308Updated last week
• pytorch / PiPPy
  Pipeline Parallelism for PyTorch
  ☆765Updated 8 months ago
• lucidrains / rotary-embedding-torch
  Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch
  ☆672Updated 5 months ago
• PiotrNawrot / nanoT5
  Fast & Simple repository for pre-training and fine-tuning T5-style models
  ☆1,003Updated 8 months ago
• ELS-RD / kernl
  Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…
  ☆1,566Updated last year
• kyegomez / Sophia
  Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.
  ☆381Updated 11 months ago
• princeton-nlp / MeZO
  [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333
  ☆1,103Updated last year
• google / flaxformer
  ☆349Updated last year
• facebookresearch / schedule_free
  Schedule-Free Optimization in PyTorch
  ☆2,150Updated 3 weeks ago
• microsoft / torchscale
  Foundation Architecture for (M)LLMs
  ☆3,074Updated last year
• idiap / fast-transformers
  Pytorch library for fast transformer implementations
  ☆1,701Updated 2 years ago
• ofirpress / attention_with_linear_biases
  Code for the ALiBi method for transformer language models (ICLR 2022)
  ☆524Updated last year
• xl0 / lovely-tensors
  Tensors, for human consumption
  ☆1,247Updated 5 months ago
• google / seqio
  Task-based datasets, preprocessing, and evaluation for sequence models.
  ☆574Updated this week
• microsoft / Tutel
  Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek FP8/FP4
  ☆814Updated this week
• srush / annotated-s4
  Implementation of https://srush.github.io/annotated-s4
  ☆494Updated 2 years ago
• facebookresearch / optimizers
  For optimization algorithm research and development.
  ☆509Updated this week
• patrick-kidger / torchtyping
  Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.
  ☆1,429Updated this week
• srush / annotated-mamba
  Annotated version of the Mamba paper
  ☆483Updated last year