Rishit-dagli / Fast-Transformer
An implementation of Additive Attention
☆150Updated 3 years ago
Alternatives and similar repositories for Fast-Transformer:
Users that are interested in Fast-Transformer are comparing it to the libraries listed below
- State of the art faster Transformer with Tensorflow 2.0 ( NLP, Computer Vision, Audio ).☆85Updated 2 years ago
- Unofficial PyTorch implementation of Fastformer based on paper "Fastformer: Additive Attention Can Be All You Need"."☆134Updated 3 years ago
- XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale☆153Updated last year
- Code for the Shortformer model, from the ACL 2021 paper by Ofir Press, Noah A. Smith and Mike Lewis.☆146Updated 3 years ago
- This project shows how to derive the total number of training tokens from a large text dataset from 🤗 datasets with Apache Beam and Data…☆24Updated 2 years ago
- Python Research Framework☆106Updated 2 years ago
- Implementation of Feedback Transformer in Pytorch☆105Updated 4 years ago
- A deep learning library based on Pytorch focussed on low resource language research and robustness☆69Updated 3 years ago
- 🛠️ Tools for Transformers compression using PyTorch Lightning ⚡☆82Updated 4 months ago
- chaii: hindi and tamil question answering☆35Updated 3 years ago
- Stabilize and achieve excellent performance with transformers☆41Updated 3 years ago
- Implementation of Fast Transformer in Pytorch☆173Updated 3 years ago
- A case study of efficient training of large language models using commodity hardware.☆68Updated 2 years ago
- Implementation of Perceiver, General Perception with Iterative Attention☆88Updated 3 years ago
- A collection of Models, Datasets, DataModules, Callbacks, Metrics, Losses and Loggers to better integrate pytorch-lightning with transfor…☆47Updated last year
- An attempt at the implementation of GLOM, Geoffrey Hinton's paper for emergent part-whole hierarchies from data☆37Updated 4 years ago
- Examples using 🤗 Hub to share and reload machine learning models☆33Updated 2 years ago
- Accelerated NLP pipelines for fast inference on CPU. Built with Transformers and ONNX runtime.☆126Updated 4 years ago
- Collection of simple functions reusable across ML projects.☆20Updated 3 years ago
- TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.☆87Updated 3 years ago
- a lightweight transformer library for PyTorch☆71Updated 3 years ago
- Functional deep learning☆108Updated 2 years ago
- Plugin for deploying MLflow models to TorchServe☆108Updated last year
- High Performance Tensorflow Data Pipeline with State of Art Augmentations and low level optimizations.☆86Updated 2 years ago
- Minimal implementation of PAWS (https://arxiv.org/abs/2104.13963) in TensorFlow.☆45Updated 3 years ago
- Version control for software 2.0☆64Updated 3 years ago
- TPU index is a package for fast similarity search over large collections of high dimension vectors on TPUs☆17Updated 3 years ago
- Implementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline.☆34Updated 4 years ago
- ☆18Updated 2 years ago
- Implements sharpness-aware minimization (https://arxiv.org/abs/2010.01412) in TensorFlow 2.☆60Updated 3 years ago