Update README.md

README.md

@@ -22,7 +22,7 @@ The codes for the pretraining are available at [retarfi/language-pretraining](ht
 
 ## Model architecture
 
-%The model architecture is the same as ELECTRA small in the [original ELECTRA implementation](https://github.com/google-research/electra); 12 layers, 256 dimensions of hidden states, and 4 attention heads.
+The model architecture is the same as ELECTRA small in the [original ELECTRA implementation](https://github.com/google-research/electra); 12 layers, 256 dimensions of hidden states, and 4 attention heads.
 
 ## Training Data
 
@@ -40,7 +40,7 @@ The vocabulary size is 32768.
 
 ## Training
 
-The models are trained with the same configuration as ELECTRA small in the [original ELECTRA paper](https://arxiv.org/abs/2003.10555); 128 tokens per instance, 128 instances per batch, and 1M training steps.
+The models are trained with the same configuration as ELECTRA small in the [original ELECTRA paper](https://arxiv.org/abs/2003.10555) except size; 128 tokens per instance, 128 instances per batch, and 1M training steps.
 
 The size of the generator is the same of the discriminator.