Code publication to the paper "Normalized Attention Without Probability Cage"
☆17Nov 9, 2021Updated 4 years ago
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 3 years ago
- 🖼️📊☆11Jun 9, 2020Updated 6 years ago
- A simple Transformer where the softmax has been replaced with normalization☆20Sep 11, 2020Updated 5 years ago
- ☆12Mar 16, 2022Updated 4 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.
- The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".☆34Jun 11, 2025Updated last year
- A JAX nn library☆21Sep 9, 2025Updated 9 months ago
- MXNet/Gluon implement of L-GM-Loss☆11Oct 17, 2018Updated 7 years ago
- A python library for highly configurable transformers - easing model architecture search and experimentation.☆48Nov 30, 2021Updated 4 years ago
- Cross-modal convolutional neural networks☆11Aug 29, 2017Updated 8 years ago
- ☆22Aug 31, 2021Updated 4 years ago
- [EMNLP 2022] Language Model Pre-Training with Sparse Latent Typing☆14Feb 10, 2023Updated 3 years ago
- Maximal Mutual Information (MMI) Tagger☆26Jun 6, 2019Updated 7 years ago
- A Clojure library for deconstructing Korean unicode syllable characters into alphabet characters☆10Nov 22, 2021Updated 4 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆21Mar 14, 2021Updated 5 years ago
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆25Jan 6, 2021Updated 5 years ago
- sigma-MoE layer☆21Jan 5, 2024Updated 2 years ago
- Estimating Q(s,s') with Deep Deterministic Dynamics Gradients☆32Feb 21, 2020Updated 6 years ago
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆51Jul 23, 2020Updated 5 years ago
- We got a stew going!☆27Oct 3, 2023Updated 2 years ago
- API for accessing the GraphLog dataset☆91May 3, 2024Updated 2 years ago
- ☆42May 18, 2020Updated 6 years ago
- ☆11Jun 21, 2022Updated 3 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Immutant adapter for Luminus☆10Sep 12, 2020Updated 5 years ago
- [CoRL 2020] COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning☆35Oct 28, 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 6 years ago
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆19Oct 9, 2022Updated 3 years ago
- A conda-smithy repository for jaxlib.☆17Apr 23, 2026Updated last month
- [ACL 2025] Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models☆39Nov 4, 2025Updated 7 months ago
- ☆11Nov 11, 2023Updated 2 years ago
- ☆14Jun 26, 2019Updated 6 years ago
- Reference implementation of algorithms for reinforcement learning and Markov decision processes.☆12Jan 28, 2021Updated 5 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Unofficially Implements https://arxiv.org/abs/2112.05682 to get Linear Memory Cost on Attention for PyTorch☆12Jan 16, 2022Updated 4 years ago
- Open Korean Text Processor wrapper for Clojure☆10Dec 1, 2018Updated 7 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 4 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
- JAX implementation of Graph Attention Networks☆13Jan 29, 2022Updated 4 years ago
- some NDK sample☆11Mar 11, 2018Updated 8 years ago