NNCP: Lossless Data Compression with Neural Networks

NNCP is an experiment to build a practical lossless data compressor with neural networks. The latest version uses a Transformer model.

The papers nncp_v2.1.pdf and nncp.pdf describe the algorithms and results of previous releases of NNCP.

The current release of NNCP is implemented in C and uses LibNC to get better performance than PyTorch.

Source: https://bellard.org/nncp/