Initial commit.

app.py

@@ -31,7 +31,7 @@ if st.button("Send"):
 
         # Query the model
         with st.spinner("Zephyr is thinking..."):
-            response = client.text_generation(user_input, parameters={"max_new_tokens": 100})
+            response = client.text_generation(user_input)
             assistant_reply = response.get("generated_text", "").strip()
 
         # Add the model's reply to the chat history