Skip to content

v0.8.5

Compare
Choose a tag to compare
@shenweichen shenweichen released this 13 Mar 09:08
· 21 commits to master since this release
a94a8ec

Change Log

Major Features and Improvements

  • Add BST model doc
  • support scaled_dot_product,additive attention type and different pooling mode in Transformer layer. doc

API changes

  • Add attention_type and output_type parameter for Transformer layer.