embedding

zsxkib/embedding-gemma-300m is a Replicate deployment of Google's EmbeddingGemma-300M model for generating 768-dimensional text embeddings, supporting flexible output dimensions via Matryoshka representation learning.

Multilingual E5-large embedding model is now available on Replicate, costing ~$0.00098 per run and completing in ~1 second on Nvidia L40S.