Update README.md

README.md

@@ -15,13 +15,19 @@ If you have more than 4GB of GPU memory, you can run it at high speed.
 Because Japanese and Chinese are used a lot during quantization, It is known that Perplexity measured using Japanese data is better than [hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4).  
 
 
+## セットアップ(setup)
+```
+pip install -q --upgrade transformers autoawq accelerate
+```
+
+
+## サンプルスクリプト(sample script)
 ```
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, AwqConfig
 
 model_id = "dahara1/llama3.1-8b-Instruct-awq"
 
-
 quantization_config = AwqConfig(
     bits=4,
     fuse_max_seq_len=512, # Note: Update this as per your use-case