Skip to content
This repository was archived by the owner on Sep 21, 2026. It is now read-only.

introduces intelligent model caching for both Hugging Face and ModelScope

Choose a tag to compare

View all tags
@LattifaiHQ LattifaiHQ released this 14 Jan 16:53
· 448 commits to main since this release
v1.2.1
a9b01d0

Full Changelog: v1.2.0...v1.2.1

Smart Model Caching

  • Automatic cache validation: Models are cached locally with date-based markers to avoid unnecessary re-downloads
  • 7-day cache validity: Cached models remain valid for 7 days before automatic refresh
  • Multi-hub support: Caching works seamlessly with both Hugging Face and ModelScope hubs
  • Unified cache management: Centralized _resolve_model_path() function handles all model downloads
Assets 2
Loading