automl / GoLULinks
GoLU, a novel, self-gated and element-wise activation function that performs well over a diverse set of tasks
☆20Updated last month
Alternatives and similar repositories for GoLU
Users that are interested in GoLU are comparing it to the libraries listed below
Sorting:
- Implementation of a Light Recurrent Unit in Pytorch☆49Updated last year
- an implementation of FAdam (Fisher Adam) in PyTorch☆49Updated 4 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆57Updated last year
- Implementation of Agent Attention in Pytorch☆91Updated last year
- Implementation of the proposed DeepCrossAttention by Heddes et al at Google research, in Pytorch☆94Updated 8 months ago
- ☆47Updated last year
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆134Updated 3 weeks ago
- A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch☆112Updated 2 months ago
- Official PyTorch Implementation for Paper "No More Adam: Learning Rate Scaling at Initialization is All You Need"☆54Updated 9 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆55Updated last year
- ☆34Updated 7 months ago
- A big_vision inspired repo that implements a generic Auto-Encoder class capable in representation learning and generative modeling.☆34Updated last year
- Official PyTorch implementation of "LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging" (ICML 2024)☆30Updated last year
- Implementation of Infini-Transformer in Pytorch☆113Updated 10 months ago
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆65Updated last year
- Distributed Optimization Infra for learning CLIP models☆27Updated last year
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆131Updated this week
- ☆186Updated last year
- Code and benchmark for the paper: "A Practitioner's Guide to Continual Multimodal Pretraining" [NeurIPS'24]☆60Updated 10 months ago
- A repository for DenseSSMs☆89Updated last year
- Code for the C2KD paper (ICASSP 2023)☆18Updated 2 years ago
- The official implementation of ICLR 2025 paper "Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models".☆15Updated 6 months ago
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆53Updated 7 months ago
- Self contained pytorch implementation of a sinkhorn based router, for mixture of experts or otherwise☆39Updated last year
- Implementation of Zorro, Masked Multimodal Transformer, in Pytorch☆96Updated 2 years ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆129Updated last week
- Official Code Implementation for 'A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models'☆20Updated last year
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆38Updated 8 months ago
- Experimental playground for benchmarking language model (LM) architectures, layers, and tricks on smaller datasets. Designed for flexible…☆84Updated 3 weeks ago
- Official implementation of Adaptive Feature Transfer (AFT)☆23Updated last year