Awesome Opensource Ai

🤗 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

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

SOTA Open Source TTS

Fully automatic censorship removal for language models

Faster Whisper transcription with CTranslate2

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

Nano vLLM

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.

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.

PyTorch native quantization for training and inference

Community maintained hardware plugin for vLLM on Ascend

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback