Add CodeLlama demo app quantized

app.py

@@ -1,11 +1,14 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline, BitsAndBytesConfig
 
-model_id = "codellama/CodeLlama-7b-hf"
+model_id = "TheBloke/CodeLlama-7B-GPTQ"  # Example 4-bit quantized model
+
+bnb_config = BitsAndBytesConfig(load_in_4bit=True, device_map="auto")
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
+    quantization_config=bnb_config,
     device_map="auto"
 )