Update README.md

README.md

@@ -12,7 +12,7 @@ widget:
 
 # PULI GPTrio (6.7 billion parameter)
 
-For further details, see [our demo site](https://juniper.nytud.hu/demo/gptrio).
+For further details and test our instruct model, see [our demo site](https://juniper.nytud.hu/demo/gptrio).
 
   - Hungarian-English-Chinese trilingual GPT-NeoX model (6.7 billion parameter)
   - Trained with EleutherAI's GPT-NeoX [github](https://github.com/EleutherAI/gpt-neox)
@@ -20,11 +20,11 @@ For further details, see [our demo site](https://juniper.nytud.hu/demo/gptrio).
 
 ## Dataset
 
-- Hungarian: 41 508 933 801 words (314 GB)
-- English: 61 906 491 82 words (391 GB)
-- Github: 6 018 366 documents (33 GB)
-- Chinese: 98 693 705 456 Chinese character (340 GB)
-  - (12 072 234 774 non Chinese token)
+- Hungarian: 41.5 billion words (314 GB)
+- English: 61.9 billion words (391 GB)
+- Github: 6 million documents (33 GB)
+- Chinese: 98.7 billion Chinese character (340 GB)
+  - (12 billion non Chinese token)
 
 ## Limitations