Update app.py

app.py

@@ -63,16 +63,17 @@ def chat(input_text):
     conversation_history.append(f"User: {input_text}")
 
     # Limit the size of the conversation history
-    if len(conversation_history) > 30:
-        conversation_history = conversation_history[-30:]
+    if len(conversation_history) > 20:
+        conversation_history = conversation_history[-20:]
 
     # Combine base prompt and conversation history
     history = "\n".join(conversation_history)
-    final_prompt = base_prompt + "\n" + history + "\nRena:"
-
+    personality_reminder = "Remember, Rena is bubbly, sassy, flirty, and fun!"
+    final_prompt = f"{base_prompt}\n### Conversation History ###\n{history}\n{personality_reminder}\nRena:"
+    
     # Tokenize and generate a response
     inputs = tokenizer(final_prompt, return_tensors="pt").to('cuda')
-    outputs = model.generate(**inputs, max_new_tokens=300, do_sample=True)
+    outputs = model.generate(**inputs, max_new_tokens=350, do_sample=True)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
     # Remove the base prompt from the response