add t12 results

language_modeling.md

@@ -51,6 +51,7 @@ Within these 100 million bytes are 205 unique tokens.
 | ---------------- | :-----: | :-----: | --- |
 | T64 (Al-Rfou et al., 2018) | 1.06 | 235M | [Character-Level Language Modeling with Deeper Self-Attention](https://arxiv.org/abs/1808.04444)
 | mLSTM + dynamic eval (Krause et al., 2017)* | 1.08 | 46M | [Dynamic Evaluation of Neural Sequence Models](https://arxiv.org/abs/1709.07432)
+| T12 (Al-Rfou et al., 2018) | 1.11 | 44M | [Character-Level Language Modeling with Deeper Self-Attention](https://arxiv.org/abs/1808.04444)
 | 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)
@@ -64,6 +65,7 @@ Within these 100 million bytes are 205 unique tokens.
 | Model           | Bit per Character (BPC) |  Number of params | Paper / Source |
 | ---------------- | :-----: | :-----: | --- |
 | T64 (Al-Rfou et al., 2018) | 1.13 | 235M | [Character-Level Language Modeling with Deeper Self-Attention](https://arxiv.org/abs/1808.04444)
+| T12 (Al-Rfou et al., 2018) | 1.18 | 44M | [Character-Level Language Modeling with Deeper Self-Attention](https://arxiv.org/abs/1808.04444)
 | mLSTM + dynamic eval (Krause et al., 2017)* | 1.19 | 45M | [Dynamic Evaluation of Neural Sequence Models](https://arxiv.org/abs/1709.07432)
 | Large mLSTM +emb +WN +VD (Krause et al., 2016) | 1.27 | 45M | [Multiplicative LSTM for sequence modelling](https://arxiv.org/abs/1609.07959)
 | Large RHN (Zilly et al., 2016) | 1.27 | 46M | [Recurrent Highway Networks](https://arxiv.org/abs/1607.03474)