Today's selected cutting-edge AI information, welcome to read 👇

🎨 Flux Ghibsky Illustration: Ghibli-style Flux LoRA model, generating high-quality landscape images.

📚 The Little Book of ML Metrics: Open-source free machine learning metrics handbook for data scientists.

🍎 Docker-OSX: Open-source tool for quickly deploying Hackintosh in Docker containers, with performance close to native.

📖 ML Retreat: AI learning path from intermediate to advanced, covering topics such as LLM construction and hallucination research.

AI Art

1. A Studio Ghibli anime style Flux LoRA model: Flux Ghibsky Illustration.

Capable of generating high-quality landscape images in Ghibli style, rich in details, with saturated colors, very suitable for generating wallpapers for sharing.

Model download: https://huggingface.co/aleksa-codes/flux-ghibsky-illustration

Open Source Projects

1. An open-source free book designed for data scientists: The Little Book of ML Metrics.

Aimed to be a quick reference manual for data scientists, covering a wide range of machine learning metrics, including regression, classification, clustering, ranking, computer vision, natural language processing, and more.

GitHub: https://github.com/NannyML/The-Little-Book-of-ML-Metrics

Hopefully, this book can help you effectively understand and utilize these metrics. Those who need it can read it.

2. An open-source free tool for quickly deploying Hackintosh: Docker-OSX.

Achieves one-click deployment and installation in Docker containers on Windows or Linux, while also providing features such as shared folders, USB device hot-swapping, and audio driver configuration.

GitHub: https://github.com/sickcodes/Docker-OSX

Supports multiple macOS versions, including High Sierra, Mojave, Catalina, etc., and importantly, achieves performance close to native experience.

The project provides detailed deployment tutorials. Those interested can install and try it out.

Learning Resources

1. An AI learning path from intermediate to advanced: ML Retreat.

Shared by a foreign tech blogger, recording personal notes and resources while learning advanced machine learning, covering in-depth understanding from basics to more advanced topics.

Currently shared notes include how to build large language models from scratch, in-depth research on LLM hallucinations, and LLMs beyond attention mechanisms.

GitHub: https://github.com/hesamsheikh/ml-retreat

Note that the author is continuously updating. If you find it helpful, you can keep following it.