Update app.py

app.py

@@ -8,13 +8,6 @@ from transformers import LlamaForCausalLM, AutoTokenizer, BitsAndBytesConfig
 # config = PeftConfig.from_pretrained("GGmorello/FLAMES")
 model = LlamaForCausalLM.from_pretrained(
     "GGmorello/FLAMES-100k",
-"""    quantization_config=BitsAndBytesConfig(
-        load_in_4bit=True,
-        bnb_4bit_quant_type="nf4",
-        bnb_4bit_use_double_quant=True,
-        bnb_4bit_compute_dtype=torch.bfloat16,
-    ),
-"""
 )
 # model = PeftModel.from_pretrained(model, "GGmorello/FLAMES-100k")