Update README.md

README.md

@@ -9,12 +9,12 @@ base_model:
 
 Gemma2 2b Japanese for Embedding generation. 
 
-Base model is Gemma2B JPN-IT published by Google in October 2024.
+Base model is Gemma2B JPN-IT published by Google in October 2024 to general public.
 
 Gemma2 2B JPN is the smallest Japanese LLM, 
-so this is very useful for practical topics. 
+so this is very useful for real world practical topics. 
 
-(all other Japanese 7B LLM  cannot be used easily 
+(all other Japanese 7B LLM  cannot be used easily at high volume 
  for embedding purposes due high inference cost).
 
 
@@ -44,9 +44,19 @@ Sample using llama-cpp
   se.encode(['こんにちは、ケビンです。よろしくおねがいします'])[0]
 ```
 
+Sample bench (ie partial):
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/645506c8e4952d1c6cb466e9/mohcBXrSkXWicJam3ErbS.png)
+
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/645506c8e4952d1c6cb466e9/00zuyIYOKWWEnHXgdEGIc.png)
+
+
+
 Access is public for research discussion purpose.
 
-To access to the weight, 
+To access to this version, 
 please contact : kevin.noel @ uzabase.com