Update README.md

README.md

@@ -27,6 +27,6 @@ This trained model is based on the Fusion-In-Decoder model, and trained on the N
 
 # Model Details
 
-Model is based on Fusion-In-Decoder, which in turn is based around the t5-base architecture. For training, we utilized text retrieval for each query, which provides a collection of relevant and non relevant passages.
+Model is based on Fusion-In-Decoder, which in turn is based on the google/flan-t5-base checkpoint. For training, we utilized text retrieval for each query, which provides a collection of relevant passages for it.
 
 We note that the passages were retrieved using a corpus based on Wikipeida.