Update README.md

README.md

@@ -45,7 +45,7 @@ Based on the hyper-parameter searching on the learning rate and batch size, we s
 
 ## Eval results
 
-|            | $n_{param}$ | $n_{layers}$ | $d_{model}$ | $n_{heads}$ | $d_{head}$ |
+|            | n_param | n_layers | d_model | n_heads | d_head |
 |------------|-------------------:|--------------------:|-------------------:|-------------------:|------------------:|
 | CPM-Small  |               109M |                  12 |                768 |                 12 |                64 |
 | CPM-Medium |               334M |                  24 |              1,024 |                 16 |                64 |