EmbeddingGemma 2 采用 Apache 2.0 许可证获好评

AI 摘要

Simon Willison 在其博客中评论了 EmbeddingGemma 2 采用 Apache 2.0 许可证一事。他认为嵌入模型不应使用闭源、专有的托管模型，因为嵌入向量通常需要大量计算并长期存储，一旦供应商停止提供该模型，用户将被迫为重新计算数百万存量向量付费。他倾向于付费使用托管服务，同时保留在供应商停服时自行运行开放权重版本或更换供应商的能力。

正文节选

6th October 2026 I really appreciate that EmbeddingGemma 2 is under the Apache 2.0 license. For embedding models in particular, I don't think it makes sense to use a closed, proprietary, hosted-only model. Most applications of embedding models involve calculating thousands or even millions of embedding vectors and storing them for later comparison. If your model is proprietary, the vendor is likely someday going to decide to stop offering that model. They'll have a better model to replace it, bu

发布时间：2026-10-07 04:37

抓取时间：2026-10-07 04:48

来源机构：Simon Willison