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.

Compression ratio

Result for enwik8:

Result for enwik9:

Program	Compr. size (bytes)	Ratio (bpb)	Program size (zip, bytes)	Total (bytes)
gzip	322 591 995	2.58	38 801	322 630 796
xz	197 331 816	1.58	36 752	197 368 568
CMIX (v18)	115 714 367	0.926	208 961	115 923 328
NNCP (2021-06-01)	108 378 032	0.867	201 620	108 579 652

* The results for the other programs are from the Large Text Compression Benchmark.

NNCP v3.1: Linux version (including CUDA support): nncp-2021-06-01.tar.gz (Changelog, readme.txt).
NNCP v3.1: Precompiled Windows version (no CUDA support): nncp-2021-06-01-win64.zip.
NNCP v2 (Python+PyTorch, GPU required): nncp_v2-2021-02-06-1.tar.gz