Stars
This repository contains a curated collection of 300+ case studies from over 80 companies, detailing practical applications and insights into machine learning (ML) system design. The contents are o…
A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
The definitive Web UI for local AI, with powerful features and easy setup.
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Repo designed to help learn the Hugging Face ecosystem (transformers, datasets, accelerate + more).
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
This repo is for the Linkedin Learning course: Applied AI: Getting Started with Hugging Face Transformers
Extraction of very large CommonCrawl WARC dataset for batch processing and language classification
⚙️ minimal paralllelizable physics simulator supporting differentiation entirely in torch
[ICCV 2025] Official repository of DiffSim: Taming Diffusion Models for Evaluating Visual Similarity
A library for directly calling PyTorch ML models from Fortran.
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.
geospatial xarray extension powered by rasterio
An implementation of chunked, compressed, N-dimensional arrays for Python.
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)
Best practices & guides on how to write distributed pytorch training code
Achieve state of the art inference performance with modern accelerators on Kubernetes
Learning in infinite dimension with neural operators.
The Qualcomm® AI Hub apps are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.