inference.py

from transformers import AutoTokenizer
from optimum.intel import OVModelForCausalLM

model_path = "helenai/ibm-granite-granite-8b-code-instruct-ov"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = OVModelForCausalLM.from_pretrained(model_path)

# change input text as desired
chat = [
    { "role": "user", "content": "Write a code to find the maximum value in a list of numbers." },
]
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
# tokenize the text
input_tokens = tokenizer(chat, return_tensors="pt")
# generate output tokens
output = model.generate(**input_tokens, max_new_tokens=100)
# decode output tokens into text
output = tokenizer.batch_decode(output)
# loop over the batch to print, in this example the batch size is 1
for i in output:
    print(i)