search

guinmoon / LLMFarm

llama and other large language models on iOS and MacOS offline using GGML library.
https://llmfarm.site
MIT License
1.05k stars 62 forks source link

Phi-2 does not work #29

Closed willfaust closed 5 months ago

willfaust commented 6 months ago

Please update llama.cpp to version b1658 or any other release after commit b9e74f9. This should allow Microsoft's Phi-2 2.7B model to work.

GoWithitRoger commented 6 months ago

Is phi-2 planned to be supported? It seems to be the most promising small model at the moment, no?

guinmoon commented 6 months ago

I plan to update llama.cpp to support Phi-2 in the LLMFarm 0.9.0 release

willfaust commented 6 months ago

Sounds good! I’m excited to test the performance.