Edit model card

Model Card for Phi-3-small-8k-instruct-4bit

馃毃 This model is a 4-bit quantized version of Microsoft's Phi-3-small-8k-instruct using bitsandbytes. You can find the unquantized version of Phi-3-small here.

Downloads last month
15
Safetensors
Model size
4.01B params
Tensor type
F32
BF16
U8
Inference Examples
Inference API (serverless) does not yet support model repos that contain custom code.