Update app.py

app.py

@@ -8,22 +8,24 @@ description = "A State-of-the-Art Large-scale Pretrained Response generation mod
 examples = [["How are you?"]]
 
 
-tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium")
-model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-medium")
+tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium", padding_side='left')
+model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-medium", padding_side='left')
 
 
 def predict(input, history=[]):
     # tokenize the new input sentence
     new_user_input_ids = tokenizer.encode(
-        input + tokenizer.eos_token, return_tensors="pt"
+        input + tokenizer.eos_token, padding=True, truncation=True, return_tensors="pt"
     )
+    #Attention Mask For Reliable Results
+    attention_mask = inputs['attention_mask']
 
     # append the new user input tokens to the chat history
     bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
 
     # generate a response
     history = model.generate(
-        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
+        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id:50256
     ).tolist()
 
     # convert the tokens to text, and then split the responses into lines