作者评 EmbeddingGemma 2：嵌入模型用闭源托管模型没有道理——向量动辄百万且要长期复用，厂商停售你就得付费重算全部存量；Apache 2.0 让他可以“付费托管、随时自持”
EmbeddingGemma 2
评分 54
导读
作者在 EmbeddingGemma 2 的 HN 讨论下留言：欣赏它以 Apache 2.0 发布。嵌入模型的应用大多要算千万级向量并存储备比，专有托管模型总有一天被厂商停掉、换成更强的新款，而存量向量仍要花钱重算（OpenAI 2024 年 4 月曾承诺“承担用户重嵌入的费用”，但那不是可指望的惯例）。他坦言自己并不想自托管——更愿意付费买托管，前提是知道对方停售时自己可以跑开放权重、或找别家托管。
主体与标签
Google#观点/评论#开源/仓库#嵌入/检索
正文
My comment on EmbeddingGemma 2 — Hacker News.
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.
Tags: google , ai , generative-ai , embeddings , gemma