Embedding models have become an important part of LLM applications, enabling tasks such as measuring ... However, embedding models are mostly based on a transformer architecture that is different from the one ... This makes it difficult to transfer the massive work being done on generative models to improve embedding

Seeing a few comments asking what can be done about data embedding with unspendable UTXOs (an issue which

This cost only grows as LLMs scale to larger embedding dimensions and context lengths.