facebookresearch / LAWTLinks
Code for papers Linear Algebra with Transformers (TMLR) and What is my Math Transformer Doing? (AI for Maths Workshop, Neurips 2022)
☆68Updated 10 months ago
Alternatives and similar repositories for LAWT
Users that are interested in LAWT are comparing it to the libraries listed below
Sorting:
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆74Updated 7 months ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- An annotated implementation of the Hyena Hierarchy paper☆33Updated 2 years ago
- ☆37Updated last year
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆50Updated 11 months ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 9 months ago
- ☆53Updated 8 months ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆83Updated last year
- Discrete Bayesian optimization with LLMs, PEFT finetuning methods, and the Laplace approximation.☆19Updated 10 months ago
- ☆29Updated 3 months ago
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated 2 years ago
- My own attempt at a long context genomics model, leveraging recent advances in long context attention modeling (Flash Attention + other h…☆53Updated last year
- Euclidean Wasserstein-2 optimal transportation☆47Updated last year
- ☆55Updated 7 months ago
- ☆32Updated 8 months ago
- A basic pure pytorch implementation of flash attention☆16Updated 7 months ago
- Code for NeurIPS 2024 paper: "Noether's razor: Learning Conserved Quantities" by Tycho F. A. van der Ouderaa, Mark van der Wilk, Pim de H…☆10Updated 8 months ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆30Updated 2 years ago
- ☆26Updated 2 years ago
- Implementation of Tranception, an attention network, paired with retrieval, that is SOTA for protein fitness prediction☆32Updated 3 years ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆78Updated 2 years ago
- Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.☆37Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆54Updated last year
- ICML 2022: Learning Iterative Reasoning through Energy Minimization☆46Updated 2 years ago
- Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk☆46Updated last year
- ☆31Updated 7 months ago
- Source-to-Source Debuggable Derivatives in Pure Python☆15Updated last year
- Differentiable Algorithms and Algorithmic Supervision.☆116Updated last year
- Implementation of the Triangle Multiplicative module, used in Alphafold2 as an efficient way to mix rows or columns of a 2d feature map, …☆32Updated 3 years ago
- Scalable and Stable Parallelization of Nonlinear RNNS☆16Updated 4 months ago