模型73°
Perplexity开源上下文嵌入模型
精选理由
Perplexity开源了新上下文嵌入模型，在两个重要基准上刷新了记录，能更好理解文档整体内容。
Perplexity开源了其最先进的上下文嵌入模型pplx-embed-v2-context-9b-preview。该模型在ConTEB基准和turbopuffer的context-bench上取得了最佳成绩。新模型采用创新训练方法，能够将整个文档的上下文编码到每个文档块中。
原文 · Aravind Srinivas
We’re open sourcing our state-of-the-art contextual embedding models, which perform best in turbopuffer’s context-bench. Perplexity @perplexity_ai We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view. pplx-embed-v2-context-9b-preview sets a new state of the art on ConTEB and @turbopuffer 's new, privately held context-bench. perplexity.ai/hub/blog/conte… 🔗 View Quoted Tweet 💬 10 🔄 4 ❤️ 62 👀 5305 📊 12 ⚡
