PiotrNawrot / dynamic-poolingLinks
Efficient Transformers with Dynamic Token Pooling
☆61Updated 2 years ago
Alternatives and similar repositories for dynamic-pooling
Users that are interested in dynamic-pooling are comparing it to the libraries listed below
Sorting:
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆136Updated last year
- The original Backpack Language Model implementation, a fork of FlashAttention☆69Updated 2 years ago
- Evaluation pipeline for the BabyLM Challenge 2023.☆76Updated last year
- FairSeq repo with Apollo optimizer☆114Updated last year
- Randomized Positional Encodings Boost Length Generalization of Transformers☆81Updated last year
- ☆19Updated 2 years ago
- ☆48Updated last year
- ☆97Updated last year
- ☆129Updated 2 years ago
- ☆53Updated last year
- ☆38Updated last year
- Standalone Product Key Memory module in Pytorch - for augmenting Transformer models☆80Updated 10 months ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆54Updated last year
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆100Updated 2 years ago
- ☆74Updated last year
- ☆51Updated 2 years ago
- The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".☆33Updated 2 weeks ago
- ☆45Updated last year
- PyTorch reimplementation of REALM and ORQA☆22Updated 3 years ago
- DEMix Layers for Modular Language Modeling☆53Updated 3 years ago
- ☆64Updated 9 months ago
- ☆55Updated 11 months ago
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆81Updated 3 years ago
- ☆67Updated 2 years ago
- The evaluation pipeline for the 2024 BabyLM Challenge.☆31Updated 7 months ago
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆65Updated last year
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆38Updated 2 years ago
- ☆21Updated 2 years ago
- Benchmark API for Multidomain Language Modeling☆24Updated 2 years ago