Update README.md

README.md

@@ -47,12 +47,12 @@ Benchmarks show significantly better English-Japanese and Japanese-English trans
 ![image/png](c3tr-version3.png)
 翻訳タスクに関しては、より大きなモデルに負けない性能を発揮します  
 元の画像クレジット Sebastian Ruder(@seb_ruder)
-(※FloRES実行時はwriting_style: journalistic、WMT23実行時はwriting_style: casualを指定。wmt23.ja-en時は一行だけ改行不揃いを手修正)
 
 For translation tasks, it performs as well as larger models.  
 Original image credit: Sebastian Ruder (@seb_ruder)
-(*When running FloRES, specify writing_style: journalistic, and when running WMT23, specify writing_style: casual. When running wmt23.ja-en, one line was manually corrected for line breaks.)
 
+翻訳ベンチマークの実行方法やその他のベンチマーク結果については[JTransBench](https://github.com/webbigdata-jp/JTransBench)を参考にしてください。  
+For instructions on how to run the translation benchmark and other benchmark results, please refer to [JTransBench](https://github.com/webbigdata-jp/JTransBench).  
 
 GoogleのウェブサービスColabを使うと無料でC3TR-Adapterを試す事が出来ます。リンク先でOpen In Colabボタンを押して起動してください。  
 You can try C3TR-Adapter for free using Google's web service Colab. Please press the Open In Colab button on the link to activate it.  
@@ -93,7 +93,7 @@ import json
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
 
-model_id = "unsloth/gemma-7b-bnb-4bit"
+model_id = "unsloth/gemma-2-9b-it-bnb-4bit"
 peft_model_id = "webbigdata/C3TR-Adapter"
 
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")