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
- 20
Hardware compatibility
Log In
to view the estimation
8-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.