styalai
/

phi-2_quantize_gptq

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Edit model card

Model Card for Model ID

Model Details

It's just the model Phi-2 by microsoft quantized by gptq in 4 bits.

Downloads last month: 19

Safetensors

Model size

601M params

Tensor type

I32

·

FP16

·