lucidrains / learning-to-expire-pytorch
An implementation of Transformer with Expire-Span, a circuit for learning which memories to retain
☆33Updated 3 years ago
Related projects: ⓘ
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆23Updated 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
- A python library for highly configurable transformers - easing model architecture search and experimentation.☆50Updated 2 years ago
- A simple implementation of a deep linear Pytorch module☆18Updated 3 years ago
- Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)☆47Updated last year
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆47Updated 2 years ago
- Implementation of COCO-LM, Correcting and Contrasting Text Sequences for Language Model Pretraining, in Pytorch☆45Updated 3 years ago
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆97Updated 3 years ago
- A GPT, made only of MLPs, in Jax☆55Updated 3 years ago
- Implementation of TableFormer, Robust Transformer Modeling for Table-Text Encoding, in Pytorch☆35Updated 2 years ago
- ☆24Updated 4 months ago
- Axial Positional Embedding for Pytorch☆61Updated 3 years ago
- GPT, but made only out of MLPs☆86Updated 3 years ago
- Code for the paper "Query-Key Normalization for Transformers"☆33Updated 3 years ago
- The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …☆15Updated 10 months ago
- Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)☆58Updated 2 years ago
- ☆63Updated 2 years ago
- My explorations into editing the knowledge and memories of an attention network☆34Updated last year
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆14Updated 3 years ago
- ☆29Updated last year
- Another attempt at a long-context / efficient transformer by me☆37Updated 2 years ago
- A variant of Transformer-XL where the memory is updated not with a queue, but with attention☆45Updated 4 years ago
- Code for the paper PermuteFormer☆43Updated 2 years ago
- Humans understand novel sentences by composing meanings and roles of core language components. In contrast, neural network models for nat…☆27Updated 4 years ago
- A 🤗-style implementation of BERT using lambda layers instead of self-attention☆70Updated 3 years ago
- ☆27Updated this week
- Code for paper "Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs"☆28Updated 2 years ago
- Standalone Product Key Memory module in Pytorch - for augmenting Transformer models☆72Updated last month
- Implementation of N-Grammer, augmenting Transformers with latent n-grams, in Pytorch☆72Updated last year
- A case study of efficient training of large language models using commodity hardware.☆68Updated 2 years ago