Transformer 相关的热门 GitHub AI项目仓库

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

huggingface

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

labmlai

A high-throughput and memory-efficient inference and serving engine for LLMs

vllm-project

Port of OpenAI's Whisper model in C/C++

ggml-org

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

huggingface

OpenMMLab Detection Toolbox and Benchmark

open-mmlab

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

lucidrains

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

karpathy

SOTA Open Source TTS

fishaudio

🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.

ml-tooling

CVPR 2025 论文和开源项目合集

amusi

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

sczhou

State-of-the-Art Text Embeddings

UKPLab

Faster Whisper transcription with CTranslate2

SYSTRAN

《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

datawhalechina

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

microsoft

Natural Language Processing Tutorial for Deep Learning Researchers

graykode

End-to-End Object Detection with Transformers

facebookresearch

pix2tex: Using a ViT to convert images of equations into LaTeX code.

lukas-blecher

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

BlinkDL

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

huggingface

Train transformer language models with reinforcement learning.

huggingface

A powerful HTTP client for Dart and Flutter, which supports global settings, Interceptors, FormData, aborting and canceling a request, files uploading and downloading, requests timeout, custom adapters, etc.

cfug

Ongoing research training transformer models at scale

NVIDIA

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

PaddlePaddle

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

jacobgil

暂无描述

google-research

This repository contains demos I made with the Transformers library by HuggingFace.

NielsRogge

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

qubvel-org

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/README.md)

alibaba

Large Language Model Text Generation Inference

huggingface

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

bigscience-workshop

Hackable and optimized Transformers building blocks, supporting a composable construction.

facebookresearch

A PyTorch implementation of the Transformer model in "Attention is All You Need".

jadore801120

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.

PaddlePaddle

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

open-mmlab

A framework for few-shot evaluation of language models.

EleutherAI

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

OptimalScale

Trax — Deep Learning with Clear Code and Speed

google

Code for the paper "Jukebox: A Generative Model for Music"

openai

Chinese version of GPT2 training code, using BERT tokenizer.

Morizeyao

Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/

zyddnys

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

jessevig

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

facebookresearch

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

EleutherAI

Decorator-based transformation, serialization, and deserialization between objects and classes.

typestack

A Jest transformer with source map support that lets you use Jest to test projects written in TypeScript.

kulshekhar

An extremely fast CSS parser, transformer, bundler, and minifier written in Rust.

parcel-bundler

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

facebookresearch

Google AI 2018 BERT pytorch implementation

codertimo

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

google-research

Model parallel transformers in JAX and Haiku

kingoflolz

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

InternLM

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

clovaai

An annotated implementation of the Transformer paper.

harvardnlp

Transformer related optimization, including BERT, GPT

NVIDIA

Taming Transformers for High-Resolution Image Synthesis

CompVis

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

sczhou

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

pytorch-labs

GoGoCode is a transformer for JavaScript/Typescript/HTML based on AST but providing a more intuitive API.

thx

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

zhouhaoyi

[CVPR 2025 Oral] VGGT: Visual Geometry Grounded Transformer

facebookresearch

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

lucidrains

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

timeseriesAI

中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

649453932

Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

bentrevett

keras implement of transformers for humans

bojone

A concise but complete full-attention transformer with a set of promising experimental features from various papers

lucidrains

JavaScript syntax tree transformer, nondestructive pretty-printer, and automatic source map generator

benjamn

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

cmhungsteve

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

AutoGPTQ

SwinIR: Image Restoration Using Swin Transformer (official repository)

JingyunLiang

【🔞🔞🔞 内含不适合未成年人阅读的图片】基于我擅长的编程、绘画、写作展开的 AI 探索和总结：StableDiffusion 是一种强大的图像生成模型，能够通过对一张图片进行演化来生成新的图片。ChatGPT 是一个基于 Transformer 的语言生成模型，它能够自动为输入的主题生成合适的文章。而 Github Copilot 是一个智能编程助手，能够加速日常编程活动。

phodal

An Open-Source Framework for Prompt-Learning.

thunlp

:zap: Primus, the creator god of the transformers & an abstraction layer for real-time to prevent module lock-in.

primus

Production First and Production Ready End-to-End Speech Recognition Toolkit

wenet-e2e

This repository contains a hand-curated resources for Prompt Engineering with a focus on Generative Pre-trained Transformer (GPT), ChatGPT, PaLM etc

promptslab

Jupyter notebooks for the Natural Language Processing with Transformers book

nlp-with-transformers

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

poloclub

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

huawei-noah

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

ThilinaRajapakse

暂无描述

openai

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Tencent

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

NVlabs

qpdf: A content-preserving PDF document transformer

qpdf

Source transformer enabling ECMAScript 6 generator functions in JavaScript-of-today.

facebook

<Beat AI> 又名 <零生万物> , 是一本专属于软件开发工程师的 AI 入门圣经，手把手带你上手写 AI。从神经网络到大模型，从高层设计到微观原理，从工程实现到算法，学完后，你会发现 AI 也并不是想象中那么高不可攀、无法战胜，Just beat it !

ibeatai

Fast inference engine for Transformer models

OpenNMT

Transformer: PyTorch Implementation of "Attention Is All You Need"

hyunwoongko

Transformer: PyTorch Implementation of "Attention Is All You Need"

hyunwoongko

暂无描述

kimiyoung

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

lyuwenyu

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

fundamentalvision

Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

dk-liang

Scalable and user friendly neural :brain: forecasting algorithms.

Nixtla

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

towhee-io