[nico]

Is someone doing embeddings<>embeddings mapping?

For example, mapping embeddings of Llama to GPT-3?

That way you can see how similar the models “understand the world”.

[fzliu]

I'm curious about this as well. There are potentially many different versions of embedding models used in production and correlating different versions together could be very important.

[sroussey]

I’d be interested to see this as well. I guess you can make a test and see what happens. Ping me if you do!

[KRAKRISMOTT]

Isn't this the whole point behind the CLIP architecture?

[nico]

Could you explain a bit more what the CLIP architecture is? Any good links to a short video demoing it? Thank you!

[KRAKRISMOTT]

https://www.pinecone.io/learn/clip-image-search/