Update app.py

app.py

@@ -21,9 +21,7 @@ def model_inference(
     input_dict, history, decoding_strategy, temperature, max_new_tokens,
     repetition_penalty, top_p, progress=gr.Progress(track_tqdm=True)
 ): 
-    buffer = "Thinking... "
-
-    yield buffer
+    yield "Processing ..."
     
     t0 = time.perf_counter()
     text = input_dict["text"]
@@ -77,11 +75,13 @@ def model_inference(
     generation_args = dict(inputs, streamer=streamer, max_new_tokens=max_new_tokens)
     generated_text = ""
 
-    print("model.generate")
     thread = Thread(target=model.generate, kwargs=generation_args)
     thread.start()
-    thread.join()
-    
+    # thread.join()
+
+    yield "Thinking ..."
+
+    buffer = ""
       
     for new_text in streamer: