Update app.py

app.py

@@ -48,20 +48,18 @@ def invoke(
 
     tokens = tokenizer.apply_chat_template(messages, return_tensors='pt', add_generation_prompt=True)
 
-    response = ""
-
-    for res in model.generate(
+    response = model.generate(
         tokens, 
-        streamer=streamer, 
         eos_token_id=model.config.eos_token_id, 
         max_new_tokens=max_tokens, 
         temperature=temperature
-    ):
-        response += res
-        yield response
+    )
+
+    print(response)
 
-    # res = tokenizer.batch_decode(out)
+    res = tokenizer.batch_decode(response)
 
+    return res
     # yield res