143 Open source projects that are alternatives of or similar to Transformer-in-PyTorch

Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering | Python3 | PyTorch | CNNs | Causality | Reasoning | LSTMs | Transformers | Multi-Head Self Attention | Published in IEEE Winter Conference on Applications of Computer Vision (WACV) 2021

Contains code for the paper "Vision Transformers are Robust Learners" (AAAI 2022).

HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision

Transformers for Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

An Open-Source Package for Chinese Open-domain Conversational Chatbot (中文闲聊对话系统，一键部署微信闲聊机器人)

Yuno is context based search engine for anime.

A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

Simple transformer implementations that I can understand

Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577

Text2Text: Cross-lingual natural language processing and generation toolkit

Super easy library for BERT based NLP models

Text Classification in Turkish Texts with Bert

Zero-Shot Text-to-Image Generation VQGAN+CLIP Dockerized

[NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining

Implementation of TransGanFormer, an all-attention GAN that combines the finding from the recent GanFormer and TransGan paper

Code for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)

State-of-the-art NLP through transformer models in a modular design and consistent APIs.

🧑‍🏫 50! Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

🌏 A zero-dependency networking solution for building modern and secure iOS, watchOS, macOS and tvOS applications.

Neural Relation Understanding: neural cardinality estimators for tabular data

General Multi-label Image Classification with Transformers

TransmogrifAI (pronounced trăns-mŏgˈrə-fī) is an AutoML library for building modular, reusable, strongly typed machine learning workflows on Apache Spark with minimal hand-tuning

Deploy transformers serverless on AWS Lambda

Library - Vanilla, ViT, DeiT, BERT, GPT

A PyTorch-based toolkit for natural language processing

Reformer, the efficient Transformer, in Pytorch

Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

Sequence to Sequence Models in PyTorch

Hashformers is a framework for hashtag segmentation with transformers.

Collection of NLP model explanations and accompanying analysis tools

Building a model to recognize incentives for landscape restoration in environmental policies from Latin America, the US and India. Bringing NLP to the world of policy analysis through an extensible framework that includes scraping, preprocessing, active learning and text analysis pipelines.

Must-read papers on Natural Language Processing (NLP)

Transformer based Bangla Speech Recognition

Transformer-based Memory Networks for Knowledge Graph Embeddings (ACL 2020) (Pytorch and Tensorflow)

Emotion recognition in conversation

Tutorials on getting started with PyTorch and TorchText for sentiment analysis.

Bangla-Bert is a pretrained bert model for Bengali language

(TPAMI 2022) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer

A library for finding knowledge neurons in pretrained transformer models.

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

[ICCV 2021] Official implementation of "Scalable Vision Transformers with Hierarchical Pooling"

Transformer based translation quality estimation

classy is a simple-to-use library for building high-performance Machine Learning models in NLP.

State of the Art Natural Language Processing

Implementation of N-Grammer, augmenting Transformers with latent n-grams, in Pytorch

LONG-TERM SERIES FORECASTING WITH QUERYSELECTOR – EFFICIENT MODEL OF SPARSEATTENTION

Load What You Need: Smaller Multilingual Transformers for Pytorch and TensorFlow 2.0.

中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

Multi-class text categorization using state-of-the-art pre-trained contextualized language models, e.g. BERT

KB국민은행에서 제공하는 경제/금융 도메인에 특화된 한국어 ALBERT 모델

Utility for analyzing Transformer based representations of language.

🔍 Haystack is an open source NLP framework that leverages Transformer models. It enables developers to implement production-ready neural search, question answering, semantic document search and summarization for a wide range of applications.

Implementation of NÜWA, state of the art attention network for text to video synthesis, in Pytorch

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

Spark-Transformers: Library for exporting Apache Spark MLLIB models to use them in any Java application with no other dependencies.

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Unofficial JAX implementations of deep learning research papers

Implementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification

[AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"