simonwillison.netarticleEmbeddingGemma 2
Simon Willison's short commentary on the release of EmbeddingGemma 2, praising its Apache 2.0 license and arguing that embedding models in particular should be open-weight rather than closed/hosted-only, since switching away from a deprecated proprietary embedding model means re-computing potentially millions of stored vectors. He notes OpenAI's 2024 offer to cover re-embedding costs as a one-off exception rather than something to rely on, and says he prefers paying a hosted provider while keeping the option to self-host the open weights if that provider ever discontinues the model.
TL;DR Simon Willison on why EmbeddingGemma 2's Apache 2.0 license matters: open weights protect you from being stuck re-embedding millions of vectors if a proprietary model gets deprecated.
Organisations named here
- OpenAI
- Simon Willison
Technologies named here
- EmbeddingGemma 2
- Gemma
Related in models
