Update app.py

app.py

@@ -45,11 +45,11 @@ def format_prompt(message, history):
         #<start_of_turn>userHow does the brain work?<end_of_turn><start_of_turn>model
         for user_prompt, bot_response in history:
             prompt += f"{user_prompt}\n"
-            print(prompt)
+            #print(prompt)
             prompt += f"{bot_response}\n"
-            print(prompt)
+            #print(prompt)
     prompt += f"<start_of_turn>user{message}<end_of_turn><start_of_turn>model"
-    print(prompt)
+    #print(prompt)
     return prompt
 
 
@@ -64,7 +64,8 @@ def chat_inf(system_prompt,prompt,history,client_choice,seed,temp,tokens,top_p,r
         hist_len=len(history)
         print(hist_len)
     in_len=len(system_prompt+prompt)+hist_len
-    print("\n#########"+str(in_len))
+    print("\n######### HIST "+str(in_len))
+    print("\n######### TOKENS "+str(tokens))
     if (in_len+tokens) > 8000:
         yield [(prompt,"Wait. I need to compress our Chat history...")]
         history=compress_history(history,client_choice,seed,temp,tokens,top_p,rep_p)