EmbeddingGemma 2 采用 Apache 2.0 许可
EmbeddingGemma 2
My comment on EmbeddingGemma 2 — Hacker News.
我对 EmbeddingGemma 2 的评论 — Hacker News。
I really appreciate that EmbeddingGemma 2 is under the Apache 2.0 license.
我非常赞赏 EmbeddingGemma 2 采用 Apache 2.0 许可证。
For embedding models in particular, I don't think it makes sense to use a closed, proprietary, hosted-only model.
特别是对于嵌入模型，我认为使用封闭、专有且仅限托管的模型是没有意义的。
Most applications of embedding models involve calculating thousands or even millions of embedding vectors and storing them for later comparison.
大多数嵌入模型的应用涉及计算数千甚至数百万个嵌入向量，并将它们存储起来以便后续比较。
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.
如果你的模型是专有的，供应商很可能有一天会决定停止提供该模型。他们会有更好的模型来替代它，但你仍然需要付费重新计算那些已存储的数百万现有向量。
(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.)
（2024年4月，OpenAI 提出“承担用户使用这些新模型重新嵌入内容的财务成本”——https://openai.com/index/gpt-4-api-general-availability/——但我认为我们不能指望每个提供商都这样做。）
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.
值得注意的是，我不想自己托管模型。我更愿意向提供商支付费用以获得托管模型，同时知道如果他们停止托管，我可以自行运行开源权重版本——或者找到其他能替我完成此操作的供应商。
Tags: google, ai, generative-ai, embeddings, gemma
标签：google, ai, generative-ai, embeddings, gemma
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力