Update app.py

app.py

@@ -19,8 +19,8 @@ from system_prompt_config import construct_input_prompt
 import json
 import atexit
 
-from huggingface_hub import login
-HF_TOKEN = os.getenv('HF_TOKEN')
+#from huggingface_hub import login
+#HF_TOKEN = os.getenv('HF_TOKEN')
 
 # From 70B code 
 system_message = "\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."
@@ -58,8 +58,8 @@ if torch.cuda.is_available():
 '''
 
 
-#if not torch.cuda.is_available():
-#    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
 
 
 if torch.cuda.is_available():
@@ -97,10 +97,10 @@ def generate(
     #   conversation.append({"role": "system", "content": system_prompt})
     
     # Construct the input prompt using the functions from the system_prompt_config module
-    # input_prompt = construct_input_prompt(chat_history, message)
+    input_prompt = construct_input_prompt(chat_history, message)
 
     # Convert input prompt to tensor
-    # input_ids = tokenizer(input_prompt, return_tensors="pt").to(model.device)
+    input_ids = tokenizer(input_prompt, return_tensors="pt").to(model.device)
 
 
     for user, assistant in chat_history: