Update app.py

app.py

@@ -13,10 +13,10 @@ base_model_name = "google/gemma-7b"
 adapter_model_name = "samidh/cope-g7bq-2c-hs.s1.5fpc.9-sx.s1.5.9o-VL.s1.5.9-HR.s5-SH.s5-l5e5-e3-d25-r8"
 
 bnb_config = BitsAndBytesConfig(
-    load_in_8bit=True,
-    #bnb_4bit_quant_type="nf4",
-    #bnb_4bit_compute_dtype=torch.bfloat16,
-    #bnb_4bit_use_double_quant=True
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16,
+    bnb_4bit_use_double_quant=True
 )
 
 model = AutoModelForCausalLM.from_pretrained(base_model_name,