Update README.md

README.md

@@ -20,3 +20,73 @@ 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)
+
+
+#Google Colabでの動作を想定
+
+# 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
+
+# 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
+
+# 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 = "Chasottco/llm-jp-3-13b-it-Chasottco"
+
+# Hugging Face Token を指定
+HF_TOKEN = ""
+
+# unslothのFastLanguageModelで元のモデルをロード。
+dtype = None # Noneにしておけば自動で設定
+load_in_4bit = True # 今回は13Bモデルを扱うためTrue
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name=model_id,
+    dtype=dtype,
+    load_in_4bit=load_in_4bit,
+    trust_remote_code=True,
+)
+
+# 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)
+
+# google drive mount(事前にデータをアップロード)
+from google.colab import drive
+drive.mount('/content/drive')
+
+# タスクとなるデータの読み込み。
+datasets = []
+with open("/content/drive/MyDrive/2024松尾研LLM/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 = ""
+
+# 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})