Update app.py

app.py

@@ -29,11 +29,11 @@ def load_models(inp):
     return gr.update(label=models[inp])
 
 def format_prompt(message, history, cust_p):
-    prompt = ""
+    prompt = "<s>"
     if history:
         for user_prompt, bot_response in history:
             prompt += f"<start_of_turn>user{user_prompt}<end_of_turn>"
-            prompt += f"<start_of_turn>model{bot_response}<end_of_turn>"
+            prompt += f"<start_of_turn>model{bot_response}<end_of_turn></s>"
             if VERBOSE==True:
                 print(prompt)
     #prompt += f"<start_of_turn>user\n{message}<end_of_turn>\n<start_of_turn>model\n"
@@ -78,7 +78,7 @@ def chat_inf(system_prompt,prompt,history,memory,client_choice,seed,temp,tokens,
     { "role": "user", "content": f"{formatted_prompt}" },
     ]
 
-        stream = client.text_generation(chat, **generate_kwargs, stream=True, details=True, return_full_text=True)
+        stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=True)
         output = ""
         for response in stream:
             output += response.token.text