metadata
base_model: Qwen/QwQ-32B-Preview
language:
- en
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/QwQ-32B-Preview/blob/main/LICENSE
tags:
- chat
- openvino
- nncf
- 8-bit
base_model_relation: quantized
This model is a quantized version of Qwen/QwQ-32B-Preview 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 = "AIFunOver/QwQ-32B-Preview-openvino-8bit"
model = OVModelForCausalLM.from_pretrained(model_id)