facebookresearch / LAWTLinks
Code for papers Linear Algebra with Transformers (TMLR) and What is my Math Transformer Doing? (AI for Maths Workshop, Neurips 2022)
☆68Updated 9 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"☆73Updated 7 months ago
- An annotated implementation of the Hyena Hierarchy paper☆33Updated 2 years ago
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆50Updated 10 months ago
- ☆53Updated 8 months ago
- 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
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆40Updated last year
- Official source code for "Graph Neural Networks for Learning Equivariant Representations of Neural Networks". In ICLR 2024 (oral).☆80Updated 10 months 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
- A MAD laboratory to improve AI architecture designs 🧪☆116Updated 5 months ago
- Implementation of Tranception, an attention network, paired with retrieval, that is SOTA for protein fitness prediction☆32Updated 2 years ago
- Official Code for Paper "Think While You Generate: Discrete Diffusion with Planned Denoising" [ICLR 2025]☆61Updated last month
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated 2 years ago
- Implementation of the Triangle Multiplicative module, used in Alphafold2 as an efficient way to mix rows or columns of a 2d feature map, …☆29Updated 3 years ago
- Explorations into the recently proposed Taylor Series Linear Attention☆99Updated 9 months ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 8 months ago
- CUDA implementation of autoregressive linear attention, with all the latest research findings☆44Updated 2 years ago
- TensorLy-Torch: Deep Tensor Learning with TensorLy and PyTorch☆77Updated 11 months ago
- ☆32Updated 8 months ago
- Beyond Straight-Through☆97Updated 2 years ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆81Updated last year
- 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
- ☆21Updated 8 months ago
- ☆29Updated 2 months ago
- Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural netwo…☆70Updated last week
- ☆31Updated 7 months ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆51Updated 2 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆100Updated 2 years ago
- Code for our paper "Generative Flow Networks for Discrete Probabilistic Modeling"☆82Updated 2 years ago
- [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)☆34Updated last year