metadata
base_model: microsoft/Phi-3-medium-4k-instruct
language:
- multilingual
license: mit
license_link: https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- code
- openvino
- nncf
- 4-bit
inference:
parameters:
temperature: 0.7
widget:
- messages:
- role: user
content: Can you provide ways to eat combinations of bananas and dragonfruits?
This model is a quantized version of microsoft/Phi-3-medium-4k-instruct 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 = "emmacall/Phi-3-medium-4k-instruct-openvino-4bit"
model = OVModelForCausalLM.from_pretrained(model_id)