learning/annotated_deep_learning_paper_implementations
1
0
Fork 0
mirror of https://github.com/labmlai/annotated_deep_learning_paper_implementations.git synced 2025-11-01 03:43:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

links

Browse Source
This commit is contained in:
Varuna Jayasiri
2021-02-05 19:20:17 +05:30
parent 8168b04440
commit 13f36c18f6
6 changed files with 12 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
labml_nn/__init__.py
View File

@ -15,12 +15,9 @@ implementations.
#### ✨ [Transformers](transformers/index.html)
[Transformers module](transformers/index.html)
contains implementations for
[multi-headed attention](transformers/mha.html)
and
[relative multi-headed attention](transformers/relative_mha.html).
* [Multi-headed attention](transformers/mha.html)
* [Transformer building blocks](transformers/models.html)
* [Relative multi-headed attention](transformers/xl/relative_mha.html).
* [GPT Architecture](transformers/gpt/index.html)
* [GLU Variants](transformers/glu_variants/simple.html)
* [kNN-LM: Generalization through Memorization](transformers/knn/index.html)

2
labml_nn/transformers/__init__.py
View File

@ -14,7 +14,7 @@ from paper [Attention Is All You Need](https://arxiv.org/abs/1706.03762),
and derivatives and enhancements of it.
* [Multi-head attention](mha.html)
* [Relative multi-head attention](relative_mha.html)
* [Relative multi-head attention](xl/relative_mha.html)
* [Transformer Encoder and Decoder Models](models.html)
* [Fixed positional encoding](positional_encoding.html)