EmbeddingGemma 2 采用 Apache 2.0 许可证
EmbeddingGemma 2
EmbeddingGemma 2 采用 Apache 2.0 许可证,作者认为嵌入模型不适合只提供闭源、专有、托管版本。嵌入应用常需计算并长期保存成千上万甚至数百万个嵌入向量,若供应商停供模型,用户可能要为重新计算存量向量付费。OpenAI 曾在 2024 年 4 月提出承担用户重新嵌入内容的费用,但作者认为这不能指望所有提供商都会这样做。
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, but you still need to pay to re-calculate those millions of stored existing vectors.
(In April 2024 OpenAI offered to "cover the financial cost of users re-embedding content with these new models" - https://openai.com/index/gpt-4-api-general-availability/ - but I don't think that's something we can rely on from every provider.)
Notably, I don't want to host the model myself. I'd much rather pay a provider for a hosted model while knowing that if they ever stop hosting it I can run the open weights version myself - or find another vendor who can do that for me.
来源:Simon Willison · simonwillison.net