for download

app.py

@@ -170,14 +170,14 @@ class WebSocketStreamingCallbackHandler(BaseCallbackHandler):
 # ------------------------ Instantiate the LLM ------------------------
 # Choose one mode: local (set use_server=False) or server (set use_server=True).
 model_path="qwen2.5-1.5b-instruct-q4_k_m.gguf"
-llm = ChatQwen(
-    temperature=0.3,
-    streaming=True,
-    max_new_tokens=512,
-    use_server=False,
-    model_path=model_path,
-    # server_url="http://localhost:8000"  # Uncomment and set if using server mode.
-)
+# llm = ChatQwen(
+#     temperature=0.3,
+#     streaming=True,
+#     max_new_tokens=512,
+#     use_server=False,
+#     model_path=model_path,
+#     # server_url="http://localhost:8000"  # Uncomment and set if using server mode.
+# )
 
 # ------------------------ FAISS and Sentence Transformer Setup ------------------------