A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch
☆127Aug 25, 2025Updated 7 months ago
Alternatives and similar repositories for gradnorm-pytorch
Users that are interested in gradnorm-pytorch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆59Oct 22, 2023Updated 2 years ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆92Jun 18, 2024Updated last year
- Implementation of a U-net complete with efficient attention as well as the latest research findings☆291May 3, 2024Updated last year
- Implementation of the Llama architecture with RLHF + Q-learning☆170Feb 1, 2025Updated last year
- Implementation of Metaformer, but in an autoregressive manner☆26Jun 21, 2022Updated 3 years ago
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆52Jul 26, 2024Updated last year
- Implementation of "compositional attention" from MILA, a multi-head attention variant that is reframed as a two-step attention process wi…☆51May 10, 2022Updated 3 years ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆122Oct 17, 2024Updated last year
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆104Dec 22, 2024Updated last year
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆126Jul 26, 2024Updated last year
- Implementation of Agent Attention in Pytorch☆93Jul 10, 2024Updated last year
- Implementation of 🌻 Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch☆92Dec 22, 2023Updated 2 years 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…☆53Oct 22, 2023Updated 2 years ago
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆253Sep 1, 2022Updated 3 years ago
- Deploy open-source AI quickly and easily - Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆50Mar 5, 2026Updated last month
- Usable implementation of Mogrifier, a circuit for enhancing LSTMs and potentially other networks, from Deepmind☆22Jun 9, 2024Updated last year
- Local Attention - Flax module for Jax☆22May 26, 2021Updated 4 years ago
- Standalone Product Key Memory module in Pytorch - for augmenting Transformer models☆87Nov 1, 2025Updated 5 months ago
- A simple cross attention that updates both the source and target in one step☆195Jul 29, 2025Updated 8 months ago
- Implementation of a holodeck, written in Pytorch☆19Nov 1, 2023Updated 2 years ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆381Jun 17, 2024Updated last year
- Implementation and explorations into Blackbox Gradient Sensing (BGS), an evolutionary strategies approach proposed in a Google Deepmind p…☆20Updated this week
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆16Aug 3, 2021Updated 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.
- Implementation of Memory-Compressed Attention, from the paper "Generating Wikipedia By Summarizing Long Sequences"☆70Apr 10, 2023Updated 3 years ago
- A wrapper for TensorBoard SummaryWriter with real-time terminal visualization using the Rich library.☆18Nov 5, 2023Updated 2 years ago
- An implementation of (Induced) Set Attention Block, from the Set Transformers paper☆67Jan 10, 2023Updated 3 years ago
- Implementation of LogAvgExp for Pytorch☆37Apr 10, 2025Updated last year
- Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind☆179Sep 12, 2024Updated last year
- Implementation of the SoftAdapt paper (techniques for adaptive loss balancing of multi-tasking neural networks)☆32Mar 16, 2024Updated 2 years ago
- Implementation of Bit Diffusion, Hinton's group's attempt at discrete denoising diffusion, in Pytorch☆356Oct 14, 2023Updated 2 years ago
- [ECCV 2024] Official PyTorch implementation of LUT "Learning with Unmasked Tokens Drives Stronger Vision Learners"☆13Dec 1, 2024Updated last year
- Implementation of the transformer proposed in "Building Blocks for a Complex-Valued Transformer Architecture"☆88Oct 13, 2023Updated 2 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Exploration into the Scaling Value Iteration Networks paper, from Schmidhuber's group☆37Sep 23, 2024Updated last year
- Implementation of Tranception, an attention network, paired with retrieval, that is SOTA for protein fitness prediction☆32Jun 19, 2022Updated 3 years ago
- Explorations into the recently proposed Taylor Series Linear Attention☆100Aug 18, 2024Updated last year
- Implementation of the algorithm detailed in paper "Evolutionary design of molecules based on deep learning and a genetic algorithm"☆24Dec 15, 2023Updated 2 years ago
- Implementation of Insertion-deletion Denoising Diffusion Probabilistic Models☆30May 31, 2022Updated 3 years ago
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆207Aug 26, 2023Updated 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☆47Jul 16, 2023Updated 2 years ago