google-deepmind / nanodoLinks
β275Updated last year
Alternatives and similar repositories for nanodo
Users that are interested in nanodo are comparing it to the libraries listed below
Sorting:
- π§± Modula software packageβ222Updated 3 weeks ago
- seqax = sequence modeling + JAXβ166Updated last month
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jaxβ643Updated this week
- Minimal yet performant LLM examples in pure JAXβ148Updated this week
- A simple library for scaling up JAX programsβ143Updated 9 months ago
- Efficient optimizersβ254Updated 3 weeks ago
- A MAD laboratory to improve AI architecture designs π§ͺβ124Updated 8 months ago
- Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUsβ523Updated this week
- JAX Synergistic Memory Inspectorβ178Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.β152Updated last month
- LoRA for arbitrary JAX models and functionsβ141Updated last year
- Named Tensors for Legible Deep Learning in JAXβ201Updated this week
- Cost aware hyperparameter tuning algorithmβ167Updated last year
- supporting pytorch FSDP for optimizersβ84Updated 8 months ago
- Minimal but scalable implementation of large language models in JAXβ35Updated last month
- Dion optimizer algorithmβ291Updated last week
- β380Updated this week
- Accelerated First Order Parallel Associative Scanβ187Updated last year
- Annotated version of the Mamba paperβ487Updated last year
- Implementation of Diffusion Transformer (DiT) in JAXβ291Updated last year
- β444Updated 10 months ago
- JAX implementation of the Llama 2 modelβ219Updated last year
- Puzzles for exploring transformersβ366Updated 2 years ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 secondsβ283Updated last month
- β233Updated 6 months ago
- β208Updated 8 months ago
- Understand and test language model architectures on synthetic tasks.β221Updated last month
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvementβ¦β389Updated this week
- β526Updated last year
- Library for reading and processing ML training data.β505Updated this week