This model is a quantized version of TheHierophant/Umbral-Devil-Hermes-Mind-V0.1 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:

python

from optimum.intel import OVModelForCausalLM

model_id = "TheHierophant/Umbral-Devil-Hermes-Mind-V0.1-openvino-8bit"
model = OVModelForCausalLM.from_pretrained(model_id)