Update README.md

README.md

@@ -1,3 +1,19 @@
 **Chatrag-Deberta** is a small lightweight LLM to predict whether a question should retrieve additional information with RAG or not.
 
-Chatrag-Deberta is based on Deberta-v3, a 304M encoder-decoder. Its initial version was fine-tuned on 20,000 examples of questions annotated by Mistral 7B.
+Chatrag-Deberta is based on Deberta-v3, a 304M encoder-decoder. Its initial version was fine-tuned on 20,000 examples of questions annotated by Mistral 7B.
+
+## Use
+
+The inference_chatrag.py file provides a typical example of inference with Chatrag-Deberta. 
+
+For every submitted text, Chatrag-Deberta will output a range of probabilities to require RAG or not. 
+
+This makes it possible to adjust a threshold of activation depending on whether more or less RAG is desirable in the system.
+
+| Query                                                    |    Prob   |  Result |
+|----------------------------------------------------------|:---------:|--------:|
+| Comment puis-je renouveler un passeport ?                |  0.988455 | RAG     |
+| Combien font deux et deux ?                              |  0.041475 | No-RAG  |
+| Écris un début de lettre de recommandation pour la Dinum |  0.103086 | No-RAG  |
+
+