RobertCsordas / moeLinks
Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"
☆37Updated last year
Alternatives and similar repositories for moe
Users that are interested in moe are comparing it to the libraries listed below
Sorting:
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- ☆46Updated last year
- ☆45Updated last year
- This repo is based on https://github.com/jiaweizzhao/GaLore☆28Updated 8 months ago
- sigma-MoE layer☆18Updated last year
- A repository for research on medium sized language models.☆76Updated last year
- ☆79Updated 9 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆97Updated 8 months ago
- Using FlexAttention to compute attention with different masking patterns☆43Updated 8 months ago
- GoldFinch and other hybrid transformer components☆45Updated 10 months ago
- ☆34Updated 11 months ago
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆47Updated last year
- ☆52Updated last year
- ☆20Updated last year
- ☆27Updated last year
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated last year
- Understanding the correlation between different LLM benchmarks☆29Updated last year
- ☆54Updated 10 months ago
- Here we will test various linear attention designs.☆58Updated last year
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆36Updated 3 months ago
- ☆31Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆54Updated 9 months ago
- RWKV model implementation☆38Updated last year
- DPO, but faster 🚀☆42Updated 5 months ago
- Efficient PScan implementation in PyTorch☆16Updated last year
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆32Updated 9 months ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆47Updated last year
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆35Updated last year
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆64Updated last year