snowflake-arctic-embed2

Snowflake 的前沿嵌入模型。 Arctic Embed 2.0 增加了多语言支持，同时不牺牲英语性能或可扩展性。

嵌入 568m

37.2K 拉取更新于 3 个月前

3 个标签

3 个月前更新

3 个月前

5de93a84837d · 1.2GB

Apache License Version 2.0, January 200

11kB

自述文件

Snowflake 很高兴地宣布发布 Arctic Embed 2.0，这是我们前沿嵌入模型的下一次迭代，现在可以支持多语言搜索。虽然我们之前的版本受到了我们的客户、合作伙伴和开源社区的好评，并导致了数百万次的下载，但我们一直收到一个要求：您能否使此模型支持多语言？ Arctic Embed 2.0 以我们之前版本的强大基础为基础，增加了多语言支持，同时不牺牲英语性能或可扩展性，以满足更广泛的用户群的需求，这些用户群涵盖了广泛的语言和应用程序。

图 1. 参数少于 1B 的开源多语言嵌入模型的单向量密集检索性能。分数是 MTEB 检索以及涵盖英语、法语、西班牙语、意大利语和德语的 CLEF (ELRA, 2006) 子集的平均 nDCG@10。

Arctic Embed 2.0 的多样化且强大的功能集

企业就绪的吞吐量和效率： Arctic Embed 2.0 模型专为大规模企业需求而构建。即使是我们的“大型”模型，其参数也远低于 1B，并提供快速、高吞吐量的嵌入功能。根据内部测试，它在 NVIDIA A10 GPU 上轻松处理每秒 100 多个文档（平均），并实现低于 10 毫秒的查询嵌入延迟，从而可以在经济实惠的硬件上进行实际部署。
不妥协的英语和非英语检索质量： 尽管 Arctic Embed 2.0 模型尺寸紧凑，但在各种英语和非英语基准数据集上都实现了令人印象深刻的 NDCG@10 分数，这表明即使对于未包含在训练配方中的语言，也具有良好的泛化能力。这些令人印象深刻的基准分数使 Arctic Embed 2.0 成为前沿检索模型中的领导者。
通过 Matryoshka Representation Learning (MRL) 实现可扩展的检索： Arctic Embed 2.0 版本包含与 Arctic Embed 1.5 中引入的相同的量化友好的 MRL 功能，允许用户在对大型数据集执行搜索时降低成本并优化规模。通过两种模型尺寸，用户只需每个向量 128 字节即可实现高质量的检索（比 OpenAI 流行的 text-embedding-3-large 模型 1 的未压缩嵌入小 96 倍）。就像 Arctic Embed 1.5 一样，Arctic Embed 2.0 模型在压缩状态下也优于几个 MRL 支持的同类产品，具有明显更低的质量下降和更高的基准分数。
真正开源： Arctic Embed 2.0 模型根据宽松的 Apache 2.0 许可证发布。

Snowflake is excited to announce the release of Arctic Embed 2.0, the next iteration of our frontier embedding models, which now empower multilingual search. While our previous releases have been well received by our customers, partners and the open source community, leading to millions of downloads, we have consistently received one request: Can you make this model multilingual? Arctic Embed 2.0 builds on the robust foundation of our previous releases, adding multilingual support without sacrificing English performance or scalability, to address the needs of an even broader user base that spans a wide range of languages and applications.

![Snowflake data](/assets/library/snowflake-arctic-embed2/0546501b-9897-4145-af38-1b352fafb89c)
Figure 1. Single-vector dense retrieval performance of open source multilingual embedding models with fewer than 1B parameters. Scores are average nDCG@10 on MTEB Retrieval and the subset of CLEF (ELRA, 2006) covering English, French, Spanish, Italian and German.

### The diverse and powerful feature set of Arctic Embed 2.0
1. **Enterprise-ready throughput and efficiency:** The Arctic Embed 2.0 models are built for large-scale enterprise demands. Even our “large” model weighs in well under 1B parameters and delivers fast, high-throughput embedding capabilities. Based on internal testing, it easily handles more than 100 documents per second (on average) on NVIDIA A10 GPUs and achieves sub-10ms query embedding latency, enabling practical deployment on budget-friendly hardware.
2. **Uncompromising quality for English and non-English retrieval:** Despite their compact sizes, both Arctic Embed 2.0 models achieve impressive NDCG@10 scores across a variety of English and non-English benchmark data sets, demonstrating a capability to generalize well even to languages not included in the training recipe. These impressive benchmark scores position Arctic Embed 2.0 as a leader among frontier retrieval models.
3. **Enabling scalable retrieval through Matryoshka Representation Learning (MRL):** The Arctic Embed 2.0 release includes the same quantization-friendly MRL functionality introduced in Arctic Embed 1.5, allowing users to reduce cost and optimize scale when performing searches over large data sets. With both model sizes, users can achieve high-quality retrieval with as few as 128 bytes per vector (96x smaller than uncompressed embeddings from OpenAI’s popular text-embedding-3-large model1). Just like Arctic Embed 1.5, the Arctic Embed 2.0 models also outshine several MRL-supporting peers with substantially lower quality degradation and higher benchmark scores in the compressed regime.
4. **Truly open source:** The Arctic Embed 2.0 models are released under the permissive Apache 2.0 license.

粘贴、拖放或单击以上传图像（.png、.jpeg、.jpg、.svg、.gif）