metadata
base_model: yujiepan/mixtral-8xtiny-random
library_name: transformers
pipeline_tag: text-generation
tags:
- openvino
- nncf
- 8-bit
inference: true
widget:
- text: Hello!
example_title: Hello world
group: Python
This model is a quantized version of yujiepan/mixtral-8xtiny-random 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 = "yujiepan/mixtral-8xtiny-random-openvino-8bit"
model = OVModelForCausalLM.from_pretrained(model_id)