refactor: simplify model initialization and remove caching

app.py

@@ -4,15 +4,15 @@ from huggingface_hub import login
 import os
 from langchain.memory import ConversationBufferMemory
 
-@st.cache_resource
-def init_model():
-    token = os.getenv("HF_TOKEN")
-    if token:
-        login(token=token)
-    return load("Rafii/f1llama")
+# @st.cache_resource
+# def init_model():
+#     token = os.getenv("HF_TOKEN")
+#     if token:
+#         login(token=token)
+#     return load("Rafii/f1llama")
     # return load("mlx-community/Mixtral-8x7B-Instruct-v0.1")
-
-model, tokenizer = init_model()
+token = os.getenv("HF_TOKEN")
+model, tokenizer = load("Rafii/f1llama")
 
 if "memory" not in st.session_state:
     st.session_state.memory = ConversationBufferMemory(return_messages=True)