Rishit-dagli / Fast-Transformer
An implementation of Fastformer: Additive Attention Can Be All You Need, a Transformer Variant in TensorFlow
☆149Updated 2 years ago
Related projects: ⓘ
- Stabilize and achieve excellent performance with transformers☆41Updated 2 years ago
- High Performance Tensorflow Data Pipeline with State of Art Augmentations and low level optimizations.☆86Updated 2 years ago
- State of the art faster Transformer with Tensorflow 2.0 ( NLP, Computer Vision, Audio ).☆85Updated last year
- Implementation of Perceiver, General Perception with Iterative Attention in TensorFlow☆86Updated 3 years ago
- Accelerated NLP pipelines for fast inference on CPU. Built with Transformers and ONNX runtime.☆125Updated 3 years ago
- Instantly improve your training performance of TensorFlow models with just 2 lines of code!☆105Updated 2 years ago
- chaii: hindi and tamil question answering☆36Updated 2 years ago
- 🛠️ Tools for Transformers compression using PyTorch Lightning ⚡☆77Updated 6 months ago
- ☆38Updated last year
- Open Source Annotation Tools for Computer Vision and NLP tasks☆52Updated 3 years ago
- Code for the Shortformer model, from the ACL 2021 paper by Ofir Press, Noah A. Smith and Mike Lewis.☆146Updated 3 years ago
- An Easy To Use PyTorch Computer Vision Library☆51Updated last year
- An open-source AutoML Library based on PyTorch☆306Updated 2 months ago
- Web Application to generate your training scripts with PyTorch Ignite☆39Updated this week
- A library to synthesize text datasets using Large Language Models (LLM)☆151Updated last year
- Python Research Framework☆107Updated last year
- Implementation of Feedback Transformer in Pytorch☆103Updated 3 years ago
- This project presents a simple framework to retrieve images similar to a query image.☆26Updated 3 years ago
- XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale☆152Updated 9 months ago
- Minimal implementation of PAWS (https://arxiv.org/abs/2104.13963) in TensorFlow.☆45Updated 3 years ago
- Unofficial PyTorch implementation of Fastformer based on paper "Fastformer: Additive Attention Can Be All You Need"."☆134Updated 3 years ago
- Implementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline.☆35Updated 4 years ago
- ☆46Updated 4 years ago
- ☆13Updated 2 years ago
- An attempt at the implementation of GLOM, Geoffrey Hinton's paper for emergent part-whole hierarchies from data☆36Updated 3 years ago
- A Simple but Powerful CNN Trainer For PyTorch☆26Updated 3 years ago
- Implementing activation functions from scratch in Tensorflow.☆36Updated 2 years ago
- A 🤗-style implementation of BERT using lambda layers instead of self-attention☆70Updated 3 years ago
- A case study of efficient training of large language models using commodity hardware.☆68Updated 2 years ago
- The "tl;dr" on a few notable transformer papers (pre-2022).☆188Updated last year