# Reload model in FP16 and merge it with LoRA weightsbase_model = AutoModelForCausalLM.from_pretrained(    model_name,    low_cpu_mem_usage=True,    return_dict=True,    torch_dtype=torch.float16,    device_map=device_map,)model = PeftModel.from_pretrained(base_model, new_model)model = model.merge_and_unload()# Reload tokenizer to save ittokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)tokenizer.add_special_tokens({'pad_token': '[PAD]'})tokenizer.pad_token = tokenizer.eos_tokentokenizer.padding_side = "right"