Update app.py

app.py

@@ -89,7 +89,7 @@ def inference(query):
     outputs = model.generate(tokenized_chat, **generation_params)
     decoded_outputs = tokenizer.batch_decode(outputs, skip_special_tokens=False)
     assistant_response = decoded_outputs[0].split("<|start_header_id|>assistant<|end_header_id|>")[-1].strip()
-    # response_ = assistant_response.replace('<|im_end|>', "")
+    response_ = assistant_response.replace('<|eot_id|>', "")
     return assistant_response
     # outputs = model.generate(tokenized_chat, **generation_params, streamer=streamer)
     # return outputs
@@ -98,8 +98,8 @@ examples = ["Translate ko to en: \n\n 은행원: 안녕하세요! BNK은행입
 
 def response(message, history):
     text = inference(message)
-    return text 
-    # for i in range(len(text)):
-    #     time.sleep(0.01)
-    #     yield text[: i + 1]
+    # return text 
+    for i in range(len(text)):
+        time.sleep(0.01)
+        yield text[: i + 1]
 gr.ChatInterface(response,examples=examples).launch()