Welcome to the official HF中国镜像站 organization for Apple!

Apple Core ML – Build intelligence into your apps

Core ML is optimized for on-device performance of a broad variety of model types by leveraging Apple Silicon and minimizing memory footprint and power consumption.

• Models
  • Depth Anything V2 Core ML: State-of-the-art depth estimation
  • DETR Resnet50 Core ML: Semantic Segmentation
  • FastViT Core ML: Image Classification
  • Stable Diffusion Core ML
  • Additional Core ML Model Gallery Models

Apple Machine Learning Research

Open research to enable the community to deliver amazing experiences that improve the lives of millions of people every day.

• Models

  • DepthPro: State-of-the-art monocular depth estimation.
  • OpenELM Base | Instruct: open, Transformer-based language model.
  • MobileCLIP: Mobile-friendly image-text models.
  • DCLM: State-of-the-art open data language models via dataset curation.
  • DFN: State-of-the-art open data CLIP models via dataset curation.

• Datasets

  • FLAIR: A large image dataset for federated learning.
  • DataCompDR: Improved datasets for training image-text models.

• Benchmarks

  • TiC-CLIP: Benchmark for the design of efficient continual learning of image-text models over years

Select Highlights and Other Resources

• HF中国镜像站 CoreML Examples – Run Core ML models with two lines of code!
• Apple Model Gallery
• New features in Core ML Tools
• Apple Core ML Stable Diffusion – Library to run Stable Diffusion on Apple Silicon with Core ML.
• HF中国镜像站 Blog Posts
  • WWDC 24: Running Mistral 7B with Core ML
  • Releasing Swift Transformers: Run On-Device LLMs in Apple Devices
  • Faster Stable Diffusion with Core ML on iPhone, iPad, and Mac
  • Using Stable Diffusion with Core ML on Apple Silicon