Some questions about text-embedding-ada-002’s embedding

[_j]

I did a big pull to characterize ada’s non-determinism.

Can text-embedding-ada-002 be made deterministic?

Is it possible that this is caused by selective availability, so that you can’t determine precisely when the running model is tweaked? Birthday problem done on 10 string outputs from embeddings (no math) text-similarity-ada-001: All outputs match text-similarity-babbage-001: All outputs match text-similarity-curie-001: All outputs match text-similarity-davinci-001: All outputs match text-search-ada-doc-001: All outputs match text-search-ada-query-001: All outputs match text-search-babbag…

It likely has something to do with the 3.5-turbo and other bases and how they are put together. logits of 3.5-turbo-instruct also show its not deterministic to the degree that even top logits sometimes flip.

Embeddings seems like something I can even do on my little 2gb nvidia pascal with the right model.