Update src/backend/chatbot.py

src/backend/chatbot.py

@@ -26,27 +26,28 @@ model = 'Llama2-7B_CPP'
 
 
 # initialize model 
-if model == 'Llama2-7B_CPP':
-    model_path = "/Users/dheym/Library/CloudStorage/OneDrive-Personal/Documents/side_projects/GRDN/src/models/llama-2-7b-chat.Q4_K_M.gguf"
-    llm = LlamaCPP(
-        # You can pass in the URL to a GGML model to download it automatically
-        #model_url=model_url,
-        # optionally, you can set the path to a pre-downloaded model instead of model_url
-        model_path=model_path,
-        temperature=0.1,
-        max_new_tokens=1000,
-        # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
-        context_window=3000,
-        # kwargs to pass to __call__()
-        generate_kwargs={},
-        # kwargs to pass to __init__()
-        # set to at least 1 to use GPU
-        model_kwargs={"n_gpu_layers": 1},
-        # transform inputs into Llama2 format
-        messages_to_prompt=messages_to_prompt,
-        completion_to_prompt=completion_to_prompt,
-        verbose=True,
-    )
+if st.session_state.demo_lite = False:
+    if model == 'Llama2-7B_CPP':
+        model_path = "/Users/dheym/Library/CloudStorage/OneDrive-Personal/Documents/side_projects/GRDN/src/models/llama-2-7b-chat.Q4_K_M.gguf"
+        llm = LlamaCPP(
+            # You can pass in the URL to a GGML model to download it automatically
+            #model_url=model_url,
+            # optionally, you can set the path to a pre-downloaded model instead of model_url
+            model_path=model_path,
+            temperature=0.1,
+            max_new_tokens=1000,
+            # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
+            context_window=3000,
+            # kwargs to pass to __call__()
+            generate_kwargs={},
+            # kwargs to pass to __init__()
+            # set to at least 1 to use GPU
+            model_kwargs={"n_gpu_layers": 1},
+            # transform inputs into Llama2 format
+            messages_to_prompt=messages_to_prompt,
+            completion_to_prompt=completion_to_prompt,
+            verbose=True,
+        )
 
 def parse_and_evaluate_text(text):
     # Find the indices of the opening and closing brackets