tml-epfl / why-weight-decayLinks
Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
☆68Updated last year
Alternatives and similar repositories for why-weight-decay
Users that are interested in why-weight-decay are comparing it to the libraries listed below
Sorting:
- Explorations into the recently proposed Taylor Series Linear Attention☆99Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆35Updated 3 years ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆127Updated 2 years ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆84Updated 11 months ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆80Updated 2 years ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆31Updated 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…☆52Updated 2 years ago
- ☆53Updated last year
- ☆48Updated last year
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- ☆58Updated last year
- [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)☆33Updated 2 years ago
- ☆41Updated last week
- Blog post☆17Updated last year
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆69Updated last year
- ☆38Updated last year
- Stick-breaking attention☆61Updated 3 months ago
- ☆45Updated 2 years ago
- Here we will test various linear attention designs.☆61Updated last year
- Using FlexAttention to compute attention with different masking patterns☆47Updated last year
- ☆86Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆55Updated last year
- Implementation of Infini-Transformer in Pytorch☆113Updated 9 months ago
- ☆83Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆40Updated 2 years ago
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆65Updated last year
- Official code for the paper "Attention as a Hypernetwork"☆44Updated last year
- ☆20Updated last year
- Language models scale reliably with over-training and on downstream tasks☆100Updated last year
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆101Updated 2 years ago