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

必要なライブラリは適宜保存してください。

bash

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

使用方法

Hugging Faceのトークンを設定

HF_TOKEN = "your_token_here"

ベースモデルとLoRAアダプターのIDを指定

python

model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "154teru/llm-jp-3-13b-it15a4_fullset_lora"

モデルとトークナイザーをロード

python

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name=model_id,
    dtype=None,
    load_in_4bit=True,
    trust_remote_code=True,
)

LoRAアダプターを統合

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

入力データを準備

JSONLフォーマットで、以下の構造を持つファイルを用意します：

json

{
    "task_id": "タスクID",
    "input": "入力テキスト"
}

推論を実行

python

FastLanguageModel.for_inference(model)
results = []
for dt in tqdm(datasets):
    input = dt["input"]
    prompt = f"""以下は、タスクを説明する指示です。要求を適切に満たす回答を書きなさい。### 指示\n{input}\n### 回答\n"""
    # 推論処理

結果を保存

python

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

出力

JSONLファイルとして保存

json

{
    "task_id": "タスクID",
    "input": "入力テキスト",
    "output": "モデルの出力"
}

Sample code(Google Colab)

model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "154teru/llm-jp-3-13b-it15a4_fullset2048_lora"

#huggingface TOKEN
HF_TOKEN = ""

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("/content/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 = ""

FastLanguageModel.for_inference(model)

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

  prompt = f"""以下は、タスクを説明する指示です。要求を適切に満たす回答を書きなさい。### 指示\n{input}\n### 回答\n"""

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

  outputs = model.generate(**inputs, max_new_tokens = 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})

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