Update README.md

README.md

@@ -12,7 +12,7 @@ tags:
 
 # Model Developers :FARADAY
 
-# ARIA is the first version of our models Llama 2 70B finetuned over 10.000 high quality french tokens. We built our own dataset for training doing an extract of the French Dataset from Enno and removing Alpaca style translated text from english.
+# ARIA is the first version of our models based on Llama 2-70B-Chat-HF. We finetuned llama 2 over 10.000 high quality french tokens. This version has been trained on a small dataset extract from  the french parliament.
 
 The goal is to increase model quality on French and general topics.