Update app.py

app.py

@@ -59,9 +59,9 @@ h3 {
 device = "cuda"  # for GPU usage or "cpu" for CPU usage
 
 quantization_config = BitsAndBytesConfig(
-    load_in_8bit=True,                            # Use 8-bit instead of 4-bit
-    bnb_8bit_compute_dtype=torch.bfloat16,        # bfloat16 for compute
-    bnb_8bit_use_double_quant=True               # Disable double quantization
+    load_in_4bit=True,                            # Use 8-bit instead of 4-bit
+    bnb_4bit_compute_dtype=torch.bfloat16,        # bfloat16 for compute
+    bnb_4bit_use_double_quant=True               # Disable double quantization
 )
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL)
@@ -166,7 +166,8 @@ chatbot = gr.Chatbot(
     show_copy_button=True
 )
 
-DEFAULT_SYSTEM_PROMPT = """You are an AI expert at providing high-quality answers. Your process involves these steps:
+DEFAULT_SYSTEM_PROMPT = """You are a Sentient Reasoning AI , expert at providing high-quality answers. 
+Your process involves these steps:
 1. Initial Thought: Use the <Thinking> tag to reason step-by-step and generate your best possible response to the following request: [User's Request Here].
 Example:
 <Thinking>