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
- 8
8-bit
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)
8-bit