Transformers

This module contains PyTorch implementations and explanations of original transformer from paper Attention Is All You Need, and derivatives and enhancements of it.

• Multi-head attention
• Transformer Encoder and Decoder Models
• Fixed positional encoding

Transformer XL

This implements Transformer XL model using relative multi-head attention

Compressive Transformer

This is an implementation of compressive transformer that extends upon Transformer XL by compressing oldest memories to give a longer attention span.

GPT Architecture

This is an implementation of GPT-2 architecture.

GLU Variants

This is an implementation of the paper GLU Variants Improve Transformer.

kNN-LM

This is an implementation of the paper Generalization through Memorization: Nearest Neighbor Language Models.

Feedback Transformer

This is an implementation of the paper Accessing Higher-level Representations in Sequential Transformers with Feedback Memory.

Switch Transformer

This is a miniature implementation of the paper Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. Our implementation only has a few million parameters and doesn’t do model parallel distributed training. It does single GPU training but we implement the concept of switching as described in the paper.

Fast Weights Transformer

This is an implementation of the paper Linear Transformers Are Secretly Fast Weight Memory Systems in PyTorch.

62from .configs import TransformerConfigs
63from .models import TransformerLayer, Encoder, Decoder, Generator, EncoderDecoder
64from .mha import MultiHeadAttention
65from labml_nn.transformers.xl.relative_mha import RelativeMultiHeadAttention