Arc Encoder Compression

Reduces inference cost by compressing context into continuous representations using a separate encoder. Generates 4-8x fewer representations than token embeddings while maintaining model performance. Works with any decoder LLM without modification or fine-tuning.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 0c17ca5380

Frequently asked questions

npx get-skill add adu2021/arc-encoder-compression