from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
)
import torch
import json
from tqdm import tqdm

# Hugging FaceのトークンとモデルID
HF_TOKEN = "your-token"  # Hugging Faceトークンを記入
model_id = "Ka3456/practice5_lora"  # 新しいモデルID

# LoRAモデルのロード
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_id,
    trust_remote_code=True,
    quantization_config=bnb_config,
    use_auth_token=HF_TOKEN,
)

tokenizer = AutoTokenizer.from_pretrained(
    model_id,
    trust_remote_code=True,
    use_auth_token=HF_TOKEN,
)

# データセットの読み込み
datasets = []
with open("elyza-tasks-100-TV_0.jsonl", "r") as f:
    item = ""
    for line in f:
        line = line.strip()
        item += line
        if item.endswith("}"):
            datasets.append(json.loads(item))
            item = ""

# モデル推論
results = []
for dt in tqdm(datasets):
    input_text = dt["input"]
    prompt = f"### 指示\n{input_text}\n### 回答\n"

    inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        use_cache=True,
        do_sample=False,
        repetition_penalty=1.2,
    )

    prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split("\n### 回答")[-1]
    results.append({"task_id": dt["task_id"], "input": input_text, "output": prediction})

# 推論結果を保存
output_file = f"{model_id}_output.jsonl"
with open(output_file, "w", encoding="utf-8") as f:
    for result in results:
        json.dump(result, f, ensure_ascii=False)
        f.write("\n")

print(f"推論結果を {output_file} に保存しました。")