Reef adds Tinker API support for LoRA training
The announcement says users can enable LoRA training with a one-line configuration change, without a local GPU.
TLDR
A project announcement says Reef now supports training with the Tinker API. It describes a continual-learning workflow: collect feedback, train with LoRA and publish versioned updates. The project also welcomes contributions to its GitHub repository.
Combined views
2.2K
1 Source, first seen ago