Switch to falcon

app.py

@@ -7,7 +7,7 @@ import os
 # Load models
 embedder = SentenceTransformer("all-MiniLM-L6-v2")
 #qa_pipeline = pipeline("text-generation", model="gpt2")  # Replace with a better QA model if desired
-qa_pipeline = pipeline("text-generation", model="mistralai/Mistral-7B-Instruct-v0.1")
+qa_pipeline = pipeline("text-generation", model="tiiuae/falcon-rw-1b")
 
 # In-memory vector index and docs
 index = None