此代碼實現多層遞歸神經網絡（RNN，LSTM和GRU）從字符級語言模型訓練/採樣。換句話說，模型採用一個文本文件作為輸入和火車一個遞歸神經網絡的學習來預測下一個字符的序列。-This code implements multi-layer Recurrent Neural Network (RNN, LSTM, and GRU) for training/sampling character-level language models. In other words the model tak