inference.py

from optimum.intel.openvino import OVModelForCausalLM
from transformers import AutoTokenizer, pipeline

# model_id should be set to either a local directory or a model available on the HuggingFace hub.
model_id = "helenai/gpt2-ov"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = OVModelForCausalLM.from_pretrained(model_id)
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
result = pipe("My name is Julien and I like to")
print(result)