Cohere Embed 在 Model Vault 上的实测结果
Some great results in here!:
AI 导读
Aidan Gomez 分享 ada_cx 使用 Cohere Embed on Model Vault 的成果：检索延迟中位数 77 ms，离线嵌入的每美元吞吐量提升 2.7 倍，向量存储占用缩小 4 倍且检索效果无明显下降，top-10 召回率达 90.7%。
正文
Some great results in here!:
By using Cohere Embed on Model Vault, @ada_cx achieved: * 77 ms median retrieval latency for faster, more accurate AI voice interactions * 2.7x greater throughput-per-dollar for offline embedding, increasing cost efficiency * 4x smaller vector storage footprint with no measurable retrieval degradation * 90.7% top-10 recall for accurate information retrieval
https://t.co/anwO9zwJtV