ADD title & description

app.py

@@ -1,6 +1,5 @@
 import gradio as gr
-import torch
-from typing import Any, Callable, Dict, Iterable, List, Optional, Tuple, Union
+from typing import List, Optional
 from transformers import BertTokenizer, BartForConditionalGeneration
 
 title = "HIT-TMG/dialogue-bart-large-chinese"
@@ -9,8 +8,6 @@ This is a seq2seq model fine-tuned on several Chinese dialogue datasets, from ba
 See some details of model card at https://huggingface.co/HIT-TMG/dialogue-bart-large-chinese .
 """
 
-# Input example: 可以 认识 一下 吗 ？[SEP]当然 可以 啦 ， 你好 。[SEP]嘿嘿 你好 ， 请问 你 最近 在 忙 什么 呢 ？[SEP]我 最近 养 了 一只 狗狗 ， 我 在 训练 它 呢 。
-
 tokenizer = BertTokenizer.from_pretrained("HIT-TMG/dialogue-bart-large-chinese")
 model = BartForConditionalGeneration.from_pretrained("HIT-TMG/dialogue-bart-large-chinese")
 
@@ -18,36 +15,6 @@ tokenizer.truncation_side = 'left'
 max_length = 512
 
 
-# def chat(history):
-#     history_prefix = "对话历史："
-#     history = history_prefix + history
-#
-#     outputs = tokenizer(history,
-#                         return_tensors='pt',
-#                         padding=True,
-#                         truncation=True,
-#                         max_length=512)
-#
-#     input_ids = outputs.input_ids
-#     output_ids = model.generate(input_ids)[0]
-#
-#     return tokenizer.decode(output_ids, skip_special_tokens=True)
-#
-#
-# chatbot = gr.Chatbot().style(color_map=("green", "pink"))
-# demo = gr.Interface(
-#     chat,
-#     inputs=gr.Textbox(lines=8, placeholder="输入你的对话历史（请以'[SEP]'作为每段对话的间隔）\nInput the dialogue history (Please split utterances by '[SEP]')"),
-#     title=title,
-#     description=description,
-#     outputs =["text"]
-# )
-#
-#
-# if __name__ == "__main__":
-#     demo.launch()
-
-
 def chat_func(input_utterance, history: Optional[List[str]] = None):
     if history is not None:
         history.append(input_utterance)
@@ -66,21 +33,47 @@ def chat_func(input_utterance, history: Optional[List[str]] = None):
 
     history.append(response)
 
-    # # convert the tokens to text, and then split the responses into lines
-    # response = tokenizer.decode(history[0]).split("<|endoftext|>")
-    # # print('decoded_response-->>'+str(response))
-    # response = [(response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)]  # convert to tuples of list
-    # # print('response-->>'+str(response))
-
     display_utterances = [(history[i], history[i + 1]) for i in range(0, len(history) - 1, 2)]
 
     return display_utterances, history
 
 
 demo = gr.Interface(fn=chat_func,
-                    inputs=["text", "state"],
+                    title=title,
+                    description=description,
+                    inputs=[gr.Textbox(lines=1, placeholder="Input current utterance"), "state"],
                     outputs=["chatbot", "state"])
 
 
 if __name__ == "__main__":
     demo.launch()
+
+
+# def chat(history):
+#     history_prefix = "对话历史："
+#     history = history_prefix + history
+#
+#     outputs = tokenizer(history,
+#                         return_tensors='pt',
+#                         padding=True,
+#                         truncation=True,
+#                         max_length=512)
+#
+#     input_ids = outputs.input_ids
+#     output_ids = model.generate(input_ids)[0]
+#
+#     return tokenizer.decode(output_ids, skip_special_tokens=True)
+#
+#
+# chatbot = gr.Chatbot().style(color_map=("green", "pink"))
+# demo = gr.Interface(
+#     chat,
+#     inputs=gr.Textbox(lines=8, placeholder="输入你的对话历史（请以'[SEP]'作为每段对话的间隔）\nInput the dialogue history (Please split utterances by '[SEP]')"),
+#     title=title,
+#     description=description,
+#     outputs =["text"]
+# )
+#
+#
+# if __name__ == "__main__":
+#     demo.launch()