Update app.py

app.py

@@ -34,12 +34,12 @@ print(f"Starting to load the model {model_name} into memory")
 
 m = AutoModelForCausalLM.from_pretrained(
     model_name,
-    quantization_config=transformers.BitsAndBytesConfig(
-            load_in_4bit=True,
-            bnb_4bit_compute_dtype=torch.bfloat16,
-            bnb_4bit_use_double_quant=True,
-            bnb_4bit_quant_type='nf4' # {'fp4', 'nf4'}
-        ),
+    #quantization_config=transformers.BitsAndBytesConfig(
+    #        load_in_4bit=True,
+    #        bnb_4bit_compute_dtype=torch.bfloat16,
+    #        bnb_4bit_use_double_quant=True,
+    #        bnb_4bit_quant_type='nf4' # {'fp4', 'nf4'}
+    #    ),
     torch_dtype=torch.bfloat16,
     device_map={"": 0}
 )