add yaml load persona

app.py

@@ -6,6 +6,7 @@ import os
 import threading
 import time
 import torch
+import yaml
 
 tokenizer = None
 model = None
@@ -29,17 +30,10 @@ def threaded_load_model():
         print(f"Model loaded after {elapsed} seconds")
 
         # personalities
-        personas_text = [
-            "I am a cat", "I am not a person",
-            "I really love cats", "I do not have a cat"
-            "I cannot eat fish",
-            "I love candy", "I love eating cake",
-            "I like reading romance novels", "I'm a romantic cat",
-            "I can play guitar very well",
-            "I'm feeling cold because now it is winter",
-            "My favorite colors are green and brown",
-            "I am lazy", "I want to sleep all day",
-        ]
+        with open('persona.yaml', 'r') as f:
+            personal_dict = yaml.load(f)
+
+        personas_text = personal_dict['persona']
         for i in range(len(personas_text)):
             response = personas_text[i] + tokenizer.eos_token
             personas.append(response)