# 必要なライブラリをインストール
%%capture
!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

python

# 必要なライブラリを読み込み
from unsloth import FastLanguageModel
from peft import PeftModel
import torch
import json
from tqdm import tqdm
import re

python

# ベースとなるモデルと学習したLoRAのアダプタ（Hugging FaceのIDを指定）。
model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "Masaki5555/llm-jp-3-13b-finetune-ver4"

python

# Hugging Face Token を指定。
HF_TOKEN = "your_Hugging_Face_Token"

python

# unslothのFastLanguageModelで元のモデルをロード。
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,
)

python

# 元のモデルにLoRAのアダプタを統合。
model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)

python

# タスクとなるデータの読み込み。
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 = ""

python

# モデルを用いてタスクの推論。
FastLanguageModel.for_inference(model)

results = []
for dt in tqdm(datasets):
  input = dt["input"]
  prompt = f"""### 指示\n{input}\n### 回答\n"""
  inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
  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, "output": prediction})

python

# 結果をjsonlで保存。
json_file_id = re.sub(".*/", "", adapter_id) 

with open(f"/content/{json_file_id}_output.jsonl", 'w', encoding='utf-8') as f:
    for result in results:
        json.dump(result, f, ensure_ascii=False)
        f.write('\n')