Update README.md

README.md

@@ -19,7 +19,8 @@ so this is very useful for real world practical topics.
 
 
 This version has been lightly fine tuned on Japanese triplet dataset 
-and with triplet loss and quantized into 4bit GGUF format:
+and with triplet loss and quantized into 4bit GGUF format.
+This is still Work In progress.
 
 
 Sample using llama-cpp
@@ -54,9 +55,10 @@ Sample bench (ie partial):
 
 
 
-Access is public for research discussion purpose.
+This is still Work In progress,
+so access is public for research discussion purpose.
 
-To access to this version, 
+To access to this version 
 please contact : kevin.noel at uzabase.com