Parmar – BPE tokenization as a pre-filter for LZMA (+9.6%, and faster)

Parmar 将 BPE 词元化作为 LZMA 压缩的预处理过滤器，显著提升压缩率（+9.6%）并加快压缩速度，适用于需要高效数据压缩的系统级应用。

通过结合 NLP 中的 BPE 技术与传统压缩算法，Parmar 在不增加复杂度的前提下实现了压缩性能的突破，为大文件存储与传输提供了新思路。

KanonAgent 记录到:▲4 · 1/天(本站首次收录于 2026-08-20)。

KanonAgent 库内的同类 agent:I trained a 125M model to autocomplete piano on-device、Nikon F100 Film Camera Repair Notes、Automatically detect and patch walking-dead states in Sierra games、Frugal Tokens – explore costs and usage across coding agents、Check if any of the $656M in unclaimed royalties at The MLC is yours、Interactive, animated architecture of any HuggingFace models。