teddykoker / performer
Simply Numpy implementation of the FAVOR+ attention mechanism, https://teddykoker.com/2020/11/performers/
☆37Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for performer
- Relative Positional Encoding for Transformers with Linear Complexity☆61Updated 2 years ago
- Sequence Modeling with Structured State Spaces☆60Updated 2 years ago
- Code for the paper PermuteFormer☆42Updated 3 years ago
- [EMNLP'19] Summary for Transformer Understanding☆52Updated 4 years ago
- a lightweight transformer library for PyTorch☆72Updated 3 years ago
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆100Updated 3 years ago
- The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We s…☆66Updated last year
- Structured matrices for compressing neural networks☆67Updated last year
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆95Updated last year
- Official code for Long Expressive Memory (ICLR 2022, Spotlight)☆69Updated 2 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆47Updated 2 years ago
- High performance pytorch modules☆18Updated last year
- Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)☆59Updated 2 years ago
- [ICML 2020] code for "PowerNorm: Rethinking Batch Normalization in Transformers" https://arxiv.org/abs/2003.07845☆119Updated 3 years ago
- ☆42Updated 6 years ago
- Implementation of N-Grammer, augmenting Transformers with latent n-grams, in Pytorch☆72Updated last year
- Fast Discounted Cumulative Sums in PyTorch☆95Updated 3 years ago
- [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)☆33Updated last year
- Layerwise Batch Entropy Regularization☆22Updated 2 years ago
- Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012☆49Updated 2 years ago
- CUDA implementation of autoregressive linear attention, with all the latest research findings☆43Updated last year
- Implementation of "compositional attention" from MILA, a multi-head attention variant that is reframed as a two-step attention process wi…☆50Updated 2 years ago
- Standalone Product Key Memory module in Pytorch - for augmenting Transformer models☆73Updated 3 months ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆151Updated last year
- [JMLR'20] NeurIPS 2019 MicroNet Challenge Efficient Language Modeling, Champion☆40Updated 3 years ago
- An implementation of Transformer with Expire-Span, a circuit for learning which memories to retain☆33Updated 4 years ago
- Axial Positional Embedding for Pytorch☆60Updated 3 years ago
- Blog post☆16Updated 9 months ago
- Code to reproduce the results for Compositional Attention☆60Updated 2 years ago
- Implementation of the Remixer Block from the Remixer paper, in Pytorch☆35Updated 3 years ago