QLoRA config
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
)

Load model
model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    quantization_config=bnb_config,
    device_map="auto",
    token = HF_TOKEN
)

Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True, token = HF_TOKEN)

model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)

datasets = []
with open(dataset_file_path, "r") as f:
    item = ""
    for line in f:
      line = line.strip()
      item += line
      if item.endswith("}"):
        datasets.append(json.loads(item))
        item = ""

results = []
for data in tqdm(datasets):

  input = data["input"]

  prompt = f"""### 指示
  {input}
  ### 回答
  """

  tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to("cuda")
  attention_mask = torch.ones_like(tokenized_input)
  with torch.no_grad():
      outputs = model.generate(
        tokenized_input,
        attention_mask=attention_mask,
        max_new_tokens=100,
        do_sample=False,       # 決定的出力
        num_beams=5,
        no_repeat_ngram_size=2,
        repetition_penalty=1.2,
        pad_token_id=tokenizer.eos_token_id
      )[0]

  output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)

  results.append({"task_id": data["task_id"], "input": input, "output": output})