model_name = "ganesha-shiisa/llm-jp-3-13b-finetune-4"

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_use_double_quant=False,
)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    quantization_config=bnb_config,
    device_map="auto",
)

tokenizer = AutoTokenizer.from_pretrained(
    model_name, trust_remote_code=True,
)

datasets = []
with open("./elyza-tasks-100-TV_0.jsonl", "r", encoding='utf-8') 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(model.device)
    with torch.no_grad():
        outputs = model.generate(
            tokenized_input,
            max_new_tokens=100,
            do_sample=False,
            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})


import re
model_name = re.sub(".*/", "", model_name)
with open(f"./{model_name}-outputs.jsonl", 'w', encoding='utf-8') as f:
    for result in results:
        # ensure_ascii=False for handling non-ASCII characters
        json.dump(result, f, ensure_ascii=False)
        f.write('\n')