styalai
/

phi-2_quantize_gptq

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

phi-2_quantize_gptq / README.md

styalai's picture

Update README.md

6c9b399 verified 3 months ago

|

raw history blame contribute delete

No virus

221 Bytes

metadata

library_name: transformers
tags: []

Model Card for Model ID

Model Details

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