Update README.md

README.md

@@ -33,6 +33,125 @@ HF_TOKEN, WB_TOKENはご自身のものに書き換えてください。<br>
   `--elyza-tasks-100-TV_0.jsonl
 ```
 
+### Usage
+Execute following code in Google Colab
+
+```python
+!pip install -U pip
+!pip install -U transformers
+!pip install -U bitsandbytes
+!pip install -U accelerate
+!pip install -U datasets
+!pip install -U peft
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+import torch
+import bitsandbytes as bnb # bitsandbytesをインポート
+import json
+import re
+from tqdm import tqdm
+from sklearn.metrics import f1_score
+
+# ベースモデルとLoRAアダプタのID
+model_id = "llm-jp/llm-jp-3-13b"
+adapter_id = "chocopan/llm-jp-3-13b-finetune-4bit"
+
+# トークナイザーのロード
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+# モデルのロード (4bit量子化)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    load_in_4bit=True, # 4bit量子化を有効にする
+    bnb_4bit_use_double_quant=True, # double quantizationを使用 (さらにメモリ効率を高める)
+    bnb_4bit_quant_type="nf4", # 量子化のタイプ (NF4が推奨)
+    torch_dtype=torch.bfloat16, # bfloat16を使用
+    device_map="auto" # デバイスマップ
+)
+
+# LoRAアダプタのロード
+model = PeftModel.from_pretrained(model, adapter_id)
+model.eval()
+
+# タスクとなるデータの読み込み。
+# 事前にデータをアップロードしてください。
+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 = ""
+
+
+# 推論の実行
+results = []
+for dt in tqdm(datasets):
+    input_text = dt["input"]
+    prompt = f"""### 指示
+    {input}
+    ### 回答
+    """
+    inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
+    # Remove token_type_ids from inputs if present
+    if "token_type_ids" in inputs:
+        del inputs["token_type_ids"]  
+    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]
+    prediction = re.sub(r"[*#]", "", prediction).strip() # 前後の空白を削除
+    results.append({
+        "task_id": dt.get("task_id", None), # task_idがない場合への対応
+        "input": input_text,
+        "prediction": prediction,
+        "expected": dt.get("output", None) # 期待データ
+    })
+
+# 評価
+exact_match_count = 0
+total_count = 0
+f1_scores = []
+
+for result in results:
+    if result["expected"] is None: # 期待データがない場合はスキップ
+        continue
+
+    total_count += 1
+    expected = result["expected"].strip() # 前後の空白を削除
+    prediction = result["prediction"].strip() # 前後の空白を削除
+
+    if prediction == expected:
+        exact_match_count += 1
+
+    # F1スコアの計算 (単語単位)
+    expected_words = expected.split()
+    prediction_words = prediction.split()
+
+    if len(expected_words) == 0 and len(prediction_words) == 0:
+        f1 = 1.0 # 両方空の場合は1.0
+    elif len(expected_words) == 0 or len(prediction_words) == 0:
+        f1 = 0.0 # 片方が空の場合は0.0
+    else:
+        f1 = f1_score(expected_words, prediction_words, average='micro') # 単語単位のF1スコア
+    f1_scores.append(f1)
+
+# 評価結果の出力
+exact_match_rate = exact_match_count / total_count if total_count > 0 else 0
+average_f1 = sum(f1_scores) / len(f1_scores) if len(f1_scores) > 0 else 0
+
+print(f"Exact Match Rate: {exact_match_rate:.4f}")
+print(f"Average F1 Score: {average_f1:.4f}")
+
+# 結果をjsonlで保存 (評価結果も追加)
+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:
+        result["exact_match"] = 1 if result["prediction"].strip() == result["expected"].strip() else 0 if result["expected"] is not None else None
+        f.write(json.dumps(result, ensure_ascii=False) + '\n')
+```
+
 ## Training Details
 ```
 training_arguments = TrainingArguments(