RobertCsordas / transformer_generalizationLinks
The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.
☆67Updated 3 years ago
Alternatives and similar repositories for transformer_generalization
Users that are interested in transformer_generalization are comparing it to the libraries listed below
Sorting:
- GPT, but made only out of MLPs☆89Updated 4 years ago
- An implementation of Transformer with Expire-Span, a circuit for learning which memories to retain☆34Updated 5 years ago
- Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper☆81Updated 4 years ago
- The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".☆34Updated 6 months ago
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆111Updated 4 years ago
- Trains Transformer model variants. Data isn't shuffled between batches.☆143Updated 3 years ago
- ☆40Updated 4 years ago
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆25Updated 4 years ago
- ☆38Updated 4 years ago
- ☆62Updated 3 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated 2 years ago
- Official code repository of the paper Learning Associative Inference Using Fast Weight Memory by Schlag et al.☆28Updated 4 years ago
- Implementation of the GBST block from the Charformer paper, in Pytorch☆119Updated 4 years ago
- Code for the paper "Implicit Representations of Meaning in Neural Language Models"☆55Updated 2 years ago
- [NeurIPS 2022] DataMUX: Data Multiplexing for Neural Networks☆60Updated 3 years ago
- [NeurIPS 2020] Official Implementation: "SMYRF: Efficient Attention using Asymmetric Clustering".☆50Updated 2 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆50Updated 3 years ago
- This repository contains the code for running the character-level Sandwich Transformers from our ACL 2020 paper on Improving Transformer …☆55Updated 4 years ago
- Code to reproduce the results for Compositional Attention☆59Updated 3 years ago
- A python library for highly configurable transformers - easing model architecture search and experimentation.☆49Updated 4 years ago
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆16Updated 4 years ago
- ☆22Updated 4 years ago
- Pytorch implementation of Compressive Transformers, from Deepmind☆163Updated 4 years ago
- Implementation of COCO-LM, Correcting and Contrasting Text Sequences for Language Model Pretraining, in Pytorch☆46Updated 4 years ago
- ☆45Updated 4 years ago
- FairSeq repo with Apollo optimizer☆114Updated 2 years ago
- Humans understand novel sentences by composing meanings and roles of core language components. In contrast, neural network models for nat…☆27Updated 5 years ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆153Updated 2 years ago
- ☆65Updated 5 years ago
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆101Updated 2 years ago