Update README.md

README.md

@@ -20,3 +20,67 @@ language:
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+# 提出用JSONLファイルの出力方法
+以下の処理により提出用JSONLファイルを出力します。
+
+※提供されているサンプルコードと同じです。
+
+## 導入パッケージ
+```
+%%capture
+!pip install unsloth
+!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+```
+## モデル取得、実行、出力保存
+```python
+from unsloth import FastLanguageModel
+import torch
+import json
+
+DATASET_JSONL_PATH="./elyza-tasks-100-TV_0.jsonl" # 評価用データセット格納パス
+
+model_name = "hi-sa-gi/llm-jp-3-13b-finetune-2"
+max_seq_length = 2048
+dtype = None
+load_in_4bit = True
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = model_name,
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+    token = "HF token",
+)
+FastLanguageModel.for_inference(model)
+
+datasets = []
+with open(DATASET_JSONL_PATH, "r") as f:
+    item = ""
+    for line in f:
+      line = line.strip()
+      item += line
+      if item.endswith("}"):
+        datasets.append(json.loads(item))
+        item = ""
+
+from tqdm import tqdm
+
+# 推論
+results = []
+for dt in tqdm(data):
+  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": data["task_id"], "input": input, "output": output})
+
+with open(f"./{model_name}_output.jsonl", 'w', encoding='utf-8') as f:
+    for result in results:
+        json.dump(result, f, ensure_ascii=False)
+        f.write('\n')