Update app.py

app.py

@@ -77,7 +77,7 @@ def generate(
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
-
+    
     streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},
@@ -90,15 +90,16 @@ def generate(
         num_beams=1,
         repetition_penalty=repetition_penalty,
     )
+    save_json("user", message)
+    
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()
-
+    
     outputs = []
     for text in streamer:
         outputs.append(text)
         yield "".join(outputs)
 
-    save_json("user", message)
     save_json("assistant", "".join(outputs))