transformer

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

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

🧑‍🏫 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, ... 🧠

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

SGLang is a high-performance serving framework for large language models and multimodal models.

OpenMMLab Detection Toolbox and Benchmark

SOTA Open Source TTS

Fully automatic censorship removal for language models

Faster Whisper transcription with CTranslate2

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

CVPR 2026 论文和开源项目合集

邱锡鹏《神经网络与深度学习》（蒲公英书）理论书 v2 与通识版

《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

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

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

Nano vLLM

Natural Language Processing Tutorial for Deep Learning Researchers

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.

A framework for few-shot evaluation of language models.

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.

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.

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

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

Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

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.

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

BertViz: Visualize Attention in Transformer Models

Chinese version of GPT2 training code, using BERT tokenizer.

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.