Change model

app.py

@@ -46,22 +46,25 @@ def getVectorIndex(docs):
 
 def getLLM():
 
+    model_path = "NousResearch/Llama-2-13b-chat-hf"
+    # model_path = "meta-llama/Llama-2-13b-chat-hf"
 
     llm = HuggingFaceLLM(
     context_window=3900,
     max_new_tokens=256,
     # generate_kwargs={"temperature": 0.25, "do_sample": False},
-    tokenizer_name="meta-llama/Llama-2-13b-chat-hf",
-    model_name="meta-llama/Llama-2-13b-chat-hf",
+    tokenizer_name=model_path,
+    model_name=model_path,
     device_map=0,
     tokenizer_kwargs={"max_length": 2048},
     # uncomment this if using CUDA to reduce memory usage
     model_kwargs={"torch_dtype": torch.float16,
-    "quantization_config": default_bnb_config,
+    # "quantization_config": default_bnb_config,
     }
     )
     return llm
 
+
 def getQueryEngine(index):
     query_engine = index.as_chat_engine(llm=getLLM())
     return query_engine
@@ -80,9 +83,9 @@ def getEmbedModel():
 
 
 
-st.set_page_config(page_title="Chat with the Streamlit docs, powered by LlamaIndex", page_icon="🦙", layout="centered", initial_sidebar_state="auto", menu_items=None)
-st.title("Chat with the Streamlit docs, powered by LlamaIndex 💬🦙")
-st.info("Check out the full tutorial to build this app in our [blog post](https://blog.streamlit.io/build-a-chatbot-with-custom-data-sources-powered-by-llamaindex/)", icon="📃")
+st.set_page_config(page_title="Project BookWorm: Your own Librarian!", page_icon="🦙", layout="centered", initial_sidebar_state="auto", menu_items=None)
+st.title("Project BookWorm: Your own Librarian!")
+st.info("Use this app to get recommendations for books that your kids will love!", icon="📃")
          
 if "messages" not in st.session_state.keys(): # Initialize the chat messages history
     st.session_state.messages = [