This is a Pytorch implementation of Reformer. It includes LSH attention, reversible network, and chunking. It has been validated with an auto-regressive task (enwik8).
Features
- Positional Embeddings
- Masking
- Documentation available
- Examples available
- Reformer Encoder Decoder Architecture
- Product Key Memory
- Customize Feedforward
- Helpers for training auto-regressive models
Categories
Machine LearningLicense
MIT LicenseFollow Reformer PyTorch
Other Useful Business Software
Go from Code to Production URL in Seconds
Skip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Reformer PyTorch!