This is a quantized GGUF version of Starling-LM-7B-alpha quantized to 4_0 and 8_0 bits.

(link to the original model : https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha)

Downloads last month
7
GGUF
Model size
7.24B params
Architecture
llama

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Dataset used to train kroonen/Starling-LM-7B-alpha-GGUF