tensor2tensor/layers/common_attention.py
# coding=utf-8
# Copyright 2023 The Tensor2Tensor Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""Utilities for attention."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function


tensor2tensor/models/transformer.py
# coding=utf-8
# Copyright 2023 The Tensor2Tensor Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""Transformer model from "Attention Is All You Need".

The Transformer model consists of an encoder and a decoder. Both are stacks
of self-attention layers followed by feed-forward layers. This model yields
good results on a number of problems, especially in NLP and machine translation.