microsoft / mup
maximal update parametrization (µP)
☆1,402Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for mup
- 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…☆1,535Updated 9 months ago
- Cramming the training of a (BERT-type) language model into limited compute.☆1,296Updated 5 months ago
- Long Range Arena for Benchmarking Efficient Transformers☆729Updated 11 months ago
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,011Updated 7 months ago
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,041Updated 5 months ago
- Convolutions for Sequence Modeling☆869Updated 5 months ago
- functorch is JAX-like composable function transforms for PyTorch.☆1,396Updated this week
- PyTorch extensions for high performance and large scale training.☆3,195Updated last week
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆851Updated last year
- ☆751Updated this week
- Language Modeling with the H3 State Space Model☆513Updated last year
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆939Updated 9 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆970Updated 3 months ago
- Tutel MoE: An Optimized Mixture-of-Experts Implementation☆735Updated this week
- Implementation of https://srush.github.io/annotated-s4☆469Updated last year
- Library for 8-bit optimizers and quantization routines.☆714Updated 2 years ago
- Foundation Architecture for (M)LLMs☆3,034Updated 7 months ago
- Pipeline Parallelism for PyTorch☆726Updated 2 months ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,223Updated last year
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆980Updated 3 months ago
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways☆821Updated 2 years ago
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆434Updated last year
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,045Updated 10 months ago
- A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.☆2,328Updated last month
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆624Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,338Updated 8 months ago
- Tensors, for human consumption☆1,113Updated 3 weeks ago
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆471Updated last year