🤗 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.

🧑‍🏫 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, ... 🧠

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

OpenMMLab Detection Toolbox and Benchmark

SOTA Open Source TTS

SGLang is a fast serving framework for large language models and vision language models.

Faster Whisper transcription with CTranslate2

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

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.

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.

Large Language Model Text Generation Inference

A framework for few-shot evaluation of language models.

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

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.

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

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

Trax — Deep Learning with Clear Code and Speed

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

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