Answer.AI 发布小型 ColBERT 检索模型，以 33M 参数超越更大模型
原标题：answerdotai/answerai-colbert-small-v1
AI 摘要
Answer.AI 发布了 answerai-colbert-small-v1，这是一个仅有 3300 万参数的 ColBERT 多向量检索模型，采用 JaColBERTv2.5 训练方法，在 BEIR 基准上超越了同等规模模型及 e5-large-v2 等更大模型。该模型兼容 Sentence Transformers、RAGatouille 和 Stanford ColBERT 等主流工具，并支持作为重排序器使用。
正文节选
--- license: apache-2.0 language: - en tags: - ColBERT - multi-vector - sentence-transformers - RAGatouille - passage-retrieval --- # answerai-colbert-small-v1 **answerai-colbert-small-v1** is a new, proof-of-concept model by [Answer.AI](https://answer.ai), showing the strong performance multi-vector models with the new [JaColBERTv2.5 training recipe](https://arxiv.org/abs/2407.20750) and some extra tweaks can reach, even with just **33 million parameters**. While being MiniLM-sized, it outpe