Update README.md

再現確認済みの実行コード全体を最後尾に追記

README.md

@@ -239,4 +239,155 @@ with open(f"{new_model_id}_output.jsonl", 'w', encoding='utf-8') as f:
 
 ---
 
+## 実行コード全体
+```python
+# 必要なライブラリのインストール
+!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+!pip install --upgrade torch
+!pip install --upgrade xformers
+!pip install ipywidgets --upgrade
+
+# Flash Attention 2のインストール
+import torch
+if torch.cuda.get_device_capability()[0] >= 8:
+    !pip install --no-deps packaging ninja einops "flash-attn>=2.6.3"
+
+# モデルとトークナイザーのロード
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from unsloth import FastLanguageModel
+
+# モデル設定
+max_seq_length = 1024
+dtype = None
+load_in_4bit = True
+model_id = "daichira/llm-jp-3-13b-finetune2"
+new_model_id = "llm-jp-3-13b-itnew9"
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name=model_id,
+    dtype=dtype,
+    load_in_4bit=load_in_4bit,
+    trust_remote_code=True,
+)
+
+# SFT用のモデル設定
+model = FastLanguageModel.get_peft_model(
+    model,
+    r=32,
+    target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
+    lora_alpha=32,
+    lora_dropout=0.05,
+    bias="none",
+    use_gradient_checkpointing="unsloth",
+    random_state=3407,
+    use_rslora=False,
+    loftq_config=None,
+    max_seq_length=max_seq_length,
+)
+
+# Hugging Faceのトークン設定
+HF_TOKEN = "your_token"
+
+# データセットの準備
+!pip install datasets
+import os
+from datasets import load_dataset
+
+dataset = load_dataset("DeL-TaiseiOzaki/Tengentoppa-sft-v1.0", split="train")
+chunk_size = 30000
+output_dir = "/content/tengentoppa_chunks"
+os.makedirs(output_dir, exist_ok=True)
+
+total_rows = len(dataset)
+num_chunks = (total_rows + chunk_size - 1) // chunk_size
+
+for i in range(num_chunks):
+    start_idx = i * chunk_size
+    end_idx = min(start_idx + chunk_size, total_rows)
+    chunk = dataset.select(range(start_idx, end_idx))
+    chunk_file = f"{output_dir}/tengentoppa_chunk_{i+1}.json"
+    chunk.to_json(chunk_file)
+    print(f"Saved chunk {i+1}/{num_chunks} to {chunk_file}")
+
+print("All chunks have been saved!")
+
+# JSON形式のデータセットをロード
+json_path = "/content/tengentoppa_chunks/tengentoppa_chunk_3.json"
+dataset = load_dataset("json", data_files=json_path)
+print(dataset)
+
+# プロンプトフォーマットの適用
+prompt = """### 指示
+{}
+### 回答
+{}"""
+EOS_TOKEN = tokenizer.eos_token
+
+def formatting_prompts_func(examples):
+    input_text = examples["instruction"]
+    output_text = examples["output"]
+    return {"formatted_text": prompt.format(input_text, output_text) + EOS_TOKEN}
+
+dataset = dataset.map(formatting_prompts_func, num_proc=4)
+
+# トレーニングの設定
+from trl import SFTTrainer
+from transformers import TrainingArguments
+from unsloth import is_bfloat16_supported
+
+trainer = SFTTrainer(
+    model=model,
+    tokenizer=tokenizer,
+    train_dataset=dataset["train"],
+    max_seq_length=max_seq_length,
+    dataset_text_field="formatted_text",
+    args=TrainingArguments(
+        per_device_train_batch_size=6,
+        gradient_accumulation_steps=4,
+        num_train_epochs=1,
+        logging_steps=50,
+        warmup_steps=500,
+        save_steps=500,
+        save_total_limit=2,
+        learning_rate=3e-4,
+        fp16=not is_bfloat16_supported(),
+        bf16=is_bfloat16_supported(),
+        group_by_length=True,
+        seed=3407,
+        output_dir="outputs",
+    ),
+)
+
+# 学習実行
+torch.cuda.empty_cache()
+trainer.train()
+
+# 推論の準備
+import json
+from tqdm import tqdm
+
+with open("/content/elyza-tasks-100-TV_0.jsonl", "r") as f:
+    datasets = [json.loads(line) for line in f if line.strip().endswith("}")]
+
+FastLanguageModel.for_inference(model)
+
+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(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_text, "output": prediction})
+
+# 推論結果の保存
+with open(f"{new_model_id}_output.jsonl", 'w', encoding='utf-8') as f:
+    for result in results:
+        json.dump(result, f, ensure_ascii=False)
+        f.write('\n')
+```
+
+
 ```