A lightweight, lightning-fast, in-process vector database

GenAI Agent Framework, the Pydantic way

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

Python port of part of the TypeAgent repo

Forked from ggerganov/llama.cpp

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

🤗 Optimum ONNX: Export your model to ONNX and run inference with ONNX Runtime

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

🤗 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.

MCAP is a modular, performant, and serialization-agnostic container file format, useful for pub/sub and robotics applications.

Enabling PyTorch on XLA Devices (e.g. Google TPU)

Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Distribute and run LLMs with a single file.

Source code of wirthuals blog

Open weights LLM from Google DeepMind.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Open source book about making Python packages.

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Automatically find issues in image datasets and practice data-centric computer vision.

Binary assets (e.g. README images) factored out into a separate repository

Extensible Python SDK for developing Flyte tasks and workflows. Simple to get started and learn and highly extensible.

Die wichtigsten APIs Deutschlands in einem Python Paket.

Fine-tuning Vision Transformers on various classification datsets

The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a neural network.

A package that returns information about audio input (e.g. note and frequency)