Building-level load forecasting has become essential with the support of fine-grained data collected by widely deployed smart meters. It acts as a basis for arranging distributed energy resources, implementing demand response, etc. Compared to aggregated-level load, the electric load of an individual building is more stochastic and thus spawns many probabilistic forecasting methods. Many of them resort to artificial neural networks (ANN) to build forecasting models. However, a well-designed forecasting model for one building may not be suitable for others, and manually designing and tuning optimal forecasting models for various buildings are tedious and time-consuming. This paper proposes an adaptive probabilistic load forecasting model to automatically generate high-performance NN structures for different buildings and produce quantile forecasts for future loads. Specifically, we cascade the long short term memory (LSTM) layer with the adjusted Differential ArchiTecture Search (DARTS) cell and use the pinball loss function to guide the model during the improved model fitting process. A case study on an open dataset shows that our proposed model has superior performance and adaptivity over the state-of-the-art static neural network model. Besides, the improved fitting process of DARTS is proved to be more time-efficient than the original one.