from google.colab import drive
drive.mount('/content/drive')

##### INITIAL SETTING #####
HF_TOKEN = Your Hagging Face Token
TASKPATH = "/content/drive/MyDrive/elyza-tasks-100-TV_0.jsonl"
OUTPUTPATH = "/content/drive/MyDrive/inference_output.jsonl"
##### ##### #### ##### #####

!pip install unsloth
!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
!pip install -U torch
!pip install -U peft

from unsloth import FastLanguageModel
from peft import PeftModel
import torch
import json
from tqdm import tqdm
import re

model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "kenakayama/llm-jp-3-13b-1216_lora"

dtype = None
load_in_4bit = True

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name=model_id,
    dtype=dtype,
    load_in_4bit=load_in_4bit,
    trust_remote_code=True,
)

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

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


FastLanguageModel.for_inference(model)

results = []
for dt in tqdm(datasets):
  input = dt["input"]

  prompt = f"""次の指示内で決められた回答形式に厳密に沿った回答をしてください。### 指示\n{input}\n### 回答\n"""

  inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)

  outputs = model.generate(**inputs, max_new_tokens = 1024, 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, "output": prediction})

with open(OUTPUTPATH, 'w', encoding='utf-8') as f:
    for result in results:
        json.dump(result, f, ensure_ascii=False)
        f.write('\n')