add timeout

app.py

@@ -19,8 +19,8 @@ def run_generation(user_text, top_p, temperature, top_k, max_new_tokens):
     model_inputs = tokenizer([user_text], return_tensors="pt").to(torch_device)
 
     # Start generation on a separate thread, so that we don't block the UI. The text is pulled from the streamer
-    # in the main thread.
-    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    # in the main thread. Adds timeout to the streamer to handle exceptions in the generation thread.
+    streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         model_inputs,
         streamer=streamer,