inference.py

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "/home/temp_model/Codestral-22B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(model_id,device_map="auto")

text = "Write me a function that computes fibonacci in Rust"
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))