ggml demo
#15
by matthoffner - opened
I've put together a demo of a ggml quantized version running on a CPU upgrade space:
Quantized Version - https://huggingface.co/NeoDim/starchat-alpha-GGML
UI - https://huggingface.co/spaces/matthoffner/starchat-alpha-ui
API - https://huggingface.co/spaces/matthoffner/starchat-alpha