MixPR：用於長上下文預處理的 Mixture-of-PageRanks 檢索器
ResearchThe Mixture-of-PageRanks Retriever for Long-Context Pre-ProcessingIn this post, we describe our Mixture-of-PageRanks RAG system, which is built to perform long-context tasks in a highly computationally efficient manner. We describe key features of the algorithm and the SOTA results it achieves across a variety of long-context benchmarks. MixPR can augment any existing foundation model, robustly outperforms frontier long-context models on a variety of benchmarks and can extend effective LLM context lengths into the billions while being able to run efficiently on CPU.December 19, 2024
Zyphra 提出 MixPR，一套結合兩類 PageRank 檢索、用於高效預處理長上下文輸入的 RAG 系統。系統按任務採用 PageRank 作全域檢索，或 Personalized PageRank 作局部檢索，並在多項長上下文基準測試取得 SOTA 結果。MixPR 可配合任何現有基礎模型，把有效 LLM 上下文長度延伸至十億級，並可在 CPU 上高效運行。
來源：Zyphra Research · zyphra.com