kv-embedding-training-free

【开发与工程】Extract high-quality embeddings from frozen decoder-only LLMs by re-routing internal key-value states without training—outperforming training-free baselines by 10% on MTEB while maintaining robustness across sequences up to 4,096 tokens.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准