Update app.py

app.py

@@ -68,7 +68,10 @@ publication_vectorstore = langchain_community.vectorstores.FAISS.load_local(
 
 # Create the callable LLM
 llm = transformers.pipeline(
-    task="text-generation", model="Qwen/Qwen2.5-7B-Instruct-AWQ", device="cuda"
+    task="text-generation", 
+    model="Qwen/Qwen2.5-7B-Instruct-AWQ", 
+    device="cuda", 
+    streamer=transformers.TextStreamer(transformers.AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct-AWQ"))
 )