from optimum.intel 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/baichuan-inc-Baichuan2-13B-Chat-ov" tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True) model = OVModelForCausalLM.from_pretrained(model_id) pipe = pipeline("text-generation", model=model, tokenizer=tokenizer) result = pipe("hello world") print(result)