from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "TheFinAI/Fin-o1-8B"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto") messages = [{ "role": "user", "content": "A company's revenue grew from $120M to $150M while operating costs rose from $90M to $105M. " "By how many percentage points did the operating margin change?",}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)output = model.generate(**inputs, max_new_tokens=1024)print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))