This repo includes .gguf built for HuggingFace/Candle. They will not work with llama.cpp.

Refer to the original repo for more details.

Downloads last month
54
GGUF
Model size
1.41B params
Architecture
undefined

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support