Update app.py

app.py

@@ -64,7 +64,7 @@ def main():
         #                    max_new_tokens=512,
         #                    temperature=0.1)
 
-        llm = CTransformers(model="google/gemma-1.1-7b-it", token=st.secrets["token"])
+        llm = CTransformers(model="meta-llama/Meta-Llama-3-8B", token=st.secrets["token"])
 
         qa = ConversationalRetrievalChain.from_llm(llm, retriever=docsearch.as_retriever())