phi-2-openvino-8bit / README.md
riacheruvu's picture
Upload README.md with huggingface_hub
06e0edd verified
metadata
base_model: microsoft/phi-2
language:
  - en
license: mit
license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
  - nlp
  - code
  - openvino
  - nncf
  - 8-bit

This model is a quantized version of microsoft/phi-2 and is converted to the OpenVINO format. This model was obtained via the nncf-quantization space with optimum-intel.

First make sure you have optimum-intel installed:

pip install optimum[openvino]

To load your model you can do as follows:

from optimum.intel import OVModelForCausalLM

model_id = "riacheruvu/phi-2-openvino-8bit"
model = OVModelForCausalLM.from_pretrained(model_id)