Update app.py

app.py

@@ -8,14 +8,14 @@ description = "A State-of-the-Art Large-scale Pretrained Response generation mod
 examples = [["How are you?"]]
 
 
-tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large", padding_side='left')
-model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
+tokenizer = AutoTokenizer.from_pretrained("TheBloke/Llama-2-7b-Chat-GPTQ")
+model = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7b-Chat-GPTQ")
 
 
 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_side='left', return_tensors="pt"
     )
 
     # append the new user input tokens to the chat history