Update app.py

app.py

@@ -52,8 +52,8 @@ generation_config = GenerationConfig(
     max_new_tokens=512,  # adjust as needed
     seed=42,
     reset=True,  # reset history (cache)
-    stream=False,  # streaming per word/token
-    threads=int(os.cpu_count() / 1),  # adjust for your CPU
+    stream=True,  # streaming per word/token
+    threads=int(os.cpu_count() / 16),  # adjust for your CPU
     stop=["<|endoftext|>"],
 )