google-research / albert

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Apache License 2.0
3.24k stars 569 forks source link

Wrong configuration of albert xlarge #180

Open zheyuye opened 4 years ago

zheyuye commented 4 years ago

It seems that there exist a conflict in the num_attention_heads which is set as 32 in the albert_config.json included in the model tar file downloaded from TF Hub instead of 16 as defined in the same page.