Update app.py

app.py

@@ -9,7 +9,7 @@ examples = [["How are you?"]]
 model_id="clibrain/Llama-2-13b-ft-instruct-es-gptq-4bit"
 config = AutoConfig.from_pretrained(model_id)
 #config.quantization_config["use_exllama"] = True
-config.quantization_config["disable_exllama"] = True
+config.quantization_config["disable_exllama"] = False
 config.quantization_config["exllama_config"] = {"version":2}
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 print("********************")