Perplexity 发布 pplx-embed-v2-late 嵌入模型，0.6B 与 9B 两个规格
pplx-embed-v2-late Technical Report
Perplexity 开源了 0.6B 和 9B 两款多模态嵌入模型，0.6B 就能打大模型，还支持 9B 建库、0.6B 查询的省资源玩法，做检索的可以试试。
Perplexity 发布 pplx-embed-v2-late 嵌入模型，包含 0.6B 和 9B 两个规格，均支持多语言与多模态的 late-interaction 检索。两个模型在文本、图像和视觉文档检索基准上取得各自尺寸级别的一流成绩，其中 0.6b 版在视觉文档检索任务上可与数倍于自身参数量的模型竞争。模型通过从 18B 教师模型做表征蒸馏训练而来，共享同一嵌入空间，支持用 9B 建索引、用低延迟的 0.6B 查询的非对称部署方式。两个模型已在 Hugging Face 上开放下载。
pplx-embed-v2-late Technical Report
In this report, we introduce pplx-embed-v2-late, a pair of 0.6B and 9B multilingual and multimodal late-interaction models. Both models achieve state-of-the-art results within their respective size classes across a range of text, image, and visual document retrieval benchmarks. On visual document retrieval tasks, pplx-embed-v2-late-0.6b is competitive with models several times larger than itself. The models are trained via representation distillation from an 18B teacher. Consequently, they share an embedding space that supports asymmetric deployment: documents can be indexed with the 9B model and queried with the low-latency 0.6B model. Both models are available at https://huggingface.co/collections/perplexity-ai/pplx-embed-v2.
