tml-epfl / why-weight-decayLinks
Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
☆66Updated 8 months ago
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:
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆80Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆73Updated 7 months ago
- ☆53Updated 8 months ago
- ☆52Updated last year
- [ICLR 2025] Official PyTorch implementation of "Forgetting Transformer: Softmax Attention with a Forget Gate"☆104Updated 2 weeks ago
- ☆19Updated 10 months ago
- ☆97Updated 2 years ago
- ☆37Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated last year
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆124Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆98Updated 9 months ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆35Updated 2 years ago
- HGRN2: Gated Linear RNNs with State Expansion☆54Updated 9 months ago
- Stick-breaking attention☆56Updated 2 months ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆30Updated last year
- Implementation of Infini-Transformer in Pytorch☆111Updated 5 months ago
- Remasking Discrete Diffusion Models with Inference-Time Scaling☆21Updated 2 months ago
- ☆79Updated 9 months ago
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆58Updated last year
- Official code for the paper "Attention as a Hypernetwork"☆36Updated 11 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆37Updated 2 years ago
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation☆40Updated 7 months ago
- [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)☆33Updated last year
- ☆29Updated 2 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆56Updated last year
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆26Updated 7 months ago
- ☆74Updated 3 months ago
- ☆31Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆37Updated last year