Update app.py

app.py

@@ -18,7 +18,7 @@ device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 model_id = "google/gemma-2-9b-it"
 tokenizer = GemmaTokenizerFast.from_pretrained(model_id, token = huggingface_token)
 
-quantization = BitsAndBytesConfig(load_in_8bit= True)
+quantization = BitsAndBytesConfig(load_in_4bit= True)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",