x-transformers and simple-hierarchical-transformer

X-transformers is a general-purpose transformer library that simple-hierarchical-transformer builds upon as an experimental architecture variant, making them complements rather than competitors.

x-transformers
79
Verified
Maintenance 20/25
Adoption 15/25
Maturity 25/25
Community 19/25
Maintenance 13/25
Adoption 16/25
Maturity 25/25
Community 11/25
Stars: 5,808
Forks: 507
Downloads:
Commits (30d): 9
Language: Python
License: MIT
Stars: 225
Forks: 13
Downloads: 321
Commits (30d): 0
Language: Python
License: MIT
No risk flags
No risk flags

About x-transformers

lucidrains/x-transformers

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Supports encoder-decoder, decoder-only (GPT), and encoder-only (BERT) architectures alongside vision transformers for image classification and multimodal tasks like image captioning and vision-language modeling. Implements experimental attention mechanisms including Flash Attention for memory-efficient training, persistent memory augmentation, and memory tokens, while offering fine-grained control over dropout strategies including stochastic depth and layer-wise dropout. Built as a PyTorch library with modular components (`TransformerWrapper`, `Encoder`, `Decoder`, `ViTransformerWrapper`) enabling flexible composition for tasks ranging from language modeling to vision-language understanding.

About simple-hierarchical-transformer

lucidrains/simple-hierarchical-transformer

Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT

Scores updated daily from GitHub, PyPI, and npm data. How scores work