Code publication to the paper "Normalized Attention Without Probability Cage"
☆17Aug 24, 2026Updated last week
Alternatives and similar repositories for normalized-attention
Users that are interested in normalized-attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆21Mar 15, 2023Updated 3 years ago
- Suite of 500 procedurally-generated NLP tasks to study language model adaptability☆21Jul 16, 2022Updated 4 years ago
- A GPT, made only of MLPs, in Jax☆59Jun 23, 2021Updated 5 years ago
- The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".☆34Jun 11, 2025Updated last year
- 🖼️📊☆11Jun 9, 2020Updated 6 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- MXNet implementation of CapsNet☆28Nov 29, 2017Updated 8 years ago
- ☆12Mar 16, 2022Updated 4 years ago
- ☆13Nov 12, 2018Updated 7 years ago
- ☆22May 3, 2022Updated 4 years ago
- The implementation of multi-branch attentive Transformer (MAT).☆33Aug 27, 2020Updated 6 years ago
- A JAX nn library☆21Sep 9, 2025Updated 11 months ago
- An implementation of Deep Generalized Canonical Correlation Analysis (DGCCA or Deep GCCA) with pytorch.☆51Jun 11, 2020Updated 6 years ago
- MXNet/Gluon implement of L-GM-Loss☆11Oct 17, 2018Updated 7 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆49Jan 27, 2022Updated 4 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Distributed SDDMM Kernel☆13Jul 8, 2022Updated 4 years ago
- A python library for highly configurable transformers - easing model architecture search and experimentation.☆48Nov 30, 2021Updated 4 years ago
- ☆22Aug 31, 2021Updated 5 years ago
- [EMNLP 2022] Language Model Pre-Training with Sparse Latent Typing☆14Feb 10, 2023Updated 3 years ago
- ☆21Mar 14, 2021Updated 5 years ago
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆25Jan 6, 2021Updated 5 years ago
- Estimating Q(s,s') with Deep Deterministic Dynamics Gradients☆32Feb 21, 2020Updated 6 years ago
- An implementation of 2021 paper by Geoffrey Hinton: "How to represent part-whole hierarchies in a neural network" in Pytorch.☆58Mar 29, 2021Updated 5 years ago
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆52Jul 23, 2020Updated 6 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆42May 18, 2020Updated 6 years ago
- Graph-based and Transition-based dependency parsers based on BiLSTMs☆30Jan 4, 2019Updated 7 years ago
- ☆11Jun 21, 2022Updated 4 years ago
- Immutant adapter for Luminus☆10Sep 12, 2020Updated 5 years ago
- Code for the 2019 TACL Paper "Trick Me If You Can: Human-in-the-loop Generation of Adversarial Question Answering Examples"☆36Jul 3, 2019Updated 7 years ago
- [CoRL 2020] COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning☆35Oct 28, 2020Updated 5 years ago
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆20Oct 9, 2022Updated 3 years ago
- A conda-smithy repository for jaxlib.☆17Updated this week
- ☆15Dec 5, 2019Updated 6 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- JAX implementation of Graph Attention Networks☆13Jan 29, 2022Updated 4 years ago
- Unofficially Implements https://arxiv.org/abs/2112.05682 to get Linear Memory Cost on Attention for PyTorch☆12Jan 16, 2022Updated 4 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, …☆39Aug 3, 2021Updated 5 years ago
- Reference implementation of algorithms for reinforcement learning and Markov decision processes.☆13Jan 28, 2021Updated 5 years ago
- Open Korean Text Processor wrapper for Clojure☆10Dec 1, 2018Updated 7 years ago
- Code and analyses related to the ExaLearn drug design efforts☆11Sep 30, 2020Updated 5 years ago
- opentqa is a open framework of the textbook question answering, which includes xtqa, mcan, cmr, mfb, mutan.☆11Mar 27, 2021Updated 5 years ago