from transformers import AutoModelForCausalLM, AutoTokenizername = "chienhsinlin/helioslm-hdl-e4b"tok = AutoTokenizer.from_pretrained(name)model = AutoModelForCausalLM.from_pretrained(name, dtype="bfloat16", device_map="auto")msgs = [{"role": "user", "content": "Write a synthesizable Verilog module for a 4-bit up/down counter with synchronous reset."}]ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)out = model.generate(ids, max_new_tokens=2048, do_sample=False)print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))