# Modelbase_model = "meta-llama/Meta-Llama-3-8B"new_model = "OrpoLlama-3-8B"# QLoRA configbnb_config = BitsAndBytesConfig(    load_in_4bit=True,    bnb_4bit_quant_type="nf4",    bnb_4bit_compute_dtype=torch_dtype,    bnb_4bit_use_double_quant=True,)# LoRA configpeft_config = LoraConfig(    r=16,    lora_alpha=32,    lora_dropout=0.05,    bias="none",    task_type="CAUSAL_LM",    target_modules=['up_proj', 'down_proj', 'gate_proj', 'k_proj', 'q_proj', 'v_proj', 'o_proj'])# Load tokenizertokenizer = AutoTokenizer.from_pretrained(base_model)# Load modelmodel = AutoModelForCausalLM.from_pretrained(    base_model,    quantization_config=bnb_config,    device_map="auto",    attn_implementation=attn_implementation)model, tokenizer = setup_chat_format(model, tokenizer)model = prepare_model_for_kbit_training(model)