lucidrains / pause-transformerLinks
Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount of time on any token
☆54Updated last year
Alternatives and similar repositories for pause-transformer
Users that are interested in pause-transformer are comparing it to the libraries listed below
Sorting:
- ☆53Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆74Updated 7 months ago
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆136Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated last week
- ☆37Updated last year
- ☆53Updated 8 months ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆89Updated last year
- ☆99Updated 2 years ago
- ☆79Updated 10 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- ☆45Updated last year
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆58Updated last year
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 8 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆99Updated 10 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆80Updated last year
- ☆53Updated last year
- This repo is based on https://github.com/jiaweizzhao/GaLore☆28Updated 9 months ago
- Using FlexAttention to compute attention with different masking patterns☆43Updated 9 months ago
- Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE …☆113Updated last year
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆37Updated last year
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆56Updated last year
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation☆40Updated 8 months ago
- some common Huggingface transformers in maximal update parametrization (µP)☆80Updated 3 years ago
- ☆78Updated 11 months ago
- Stick-breaking attention☆57Updated this week
- Latent Diffusion Language Models☆68Updated last year
- nanoGPT-like codebase for LLM training☆98Updated last month
- ☆81Updated last year