metadata
base_model: WeiboAI/VibeThinker-1.5B
language:
- en
library_name: transformers
license: mit
pipeline_tag: text-generation
tags:
- math
- code
- gpqa
- openvino
- nncf
- 4-bit
This model is a quantized version of WeiboAI/VibeThinker-1.5B 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 = "user0199939/VibeThinker-1.5B-openvino-4bit"
model = OVModelForCausalLM.from_pretrained(model_id)