Jan now supports Cohere’s new models Aya 23 (8B) & Aya 23 (35B) and Microsoft’s Phi-3-Medium.
More GGUF models can run in Jan - we rebased to llama.cpp b2961.
Huge shoutouts to ggerganov and contributors for llama.cpp, and Bartowski for GGUF models.
For more details, see the GitHub release notes.