add large mlstm result for hutter prize dataset

language_modeling.md

@@ -52,9 +52,9 @@ Within these 100 million bytes are 205 unique tokens.
 | mLSTM + dynamic eval (Krause et al., 2017)* | 1.08 | 46M | [Dynamic Evaluation of Neural Sequence Models](https://arxiv.org/abs/1709.07432)
 | 3 layer AWD-LSTM (Merity et al., 2018)  | 1.232 | 47M | [An Analysis of Neural Language Modeling at Multiple Scales](https://arxiv.org/abs/1803.08240) |
 | Large FS-LSTM-4 (Mujika et al., 2017) | 1.245 | 47M | [Fast-Slow Recurrent Neural Networks](https://arxiv.org/abs/1705.08639) |
+| Large mLSTM +emb +WN +VD (Krause et al., 2017) | 1.24 | 46M | [Multiplicative LSTM for sequence modelling](https://arxiv.org/abs/1609.07959)
 | FS-LSTM-4 (Mujika et al., 2017) | 1.277 | 27M | [Fast-Slow Recurrent Neural Networks](https://arxiv.org/abs/1705.08639) |
 | Large RHN (Zilly et al., 2016) | 1.27 | 46M | [Recurrent Highway Networks](https://arxiv.org/abs/1607.03474)
-| FS-LSTM-2 (Mujika et al., 2017) | 1.290 | 27M | [Fast-Slow Recurrent Neural Networks](https://arxiv.org/abs/1705.08639) |
 
 
 ### Text8