diff --git a/pytorch_pretrained_bert/modeling.py b/pytorch_pretrained_bert/modeling.py index acdc741f..83562ea5 100644 --- a/pytorch_pretrained_bert/modeling.py +++ b/pytorch_pretrained_bert/modeling.py @@ -439,8 +439,8 @@ class PreTrainedBertModel(nn.Module): # cf https://github.com/pytorch/pytorch/pull/5617 module.weight.data.normal_(mean=0.0, std=self.config.initializer_range) elif isinstance(module, BertLayerNorm): - module.bias.data.normal_(mean=0.0, std=self.config.initializer_range) - module.weight.data.normal_(mean=0.0, std=self.config.initializer_range) + module.bias.data.zero_() + module.weight.data.fill_(1.0) if isinstance(module, nn.Linear) and module.bias is not None: module.bias.data.zero_()