Large language models are having their Stable Diffusion moment

Re:Large language models are having their Stable Diffusion m... by hnhg on Saturday March 11, 2023 @08:24PM (#35115221)

Yes. You can break the document up and index each part and then tackle it that way. It works surprisingly well. The 4096 token limit is tied to the attention window, not an API restriction.

[ Parent | on HN ]

Re:Large language models are having their Stable Diffusion m... by jerpint on Saturday March 11, 2023 @08:27PM (#35115254)

Attention doesn’t have a window, unless you mean there’s a limit to the number of absolute positional embeddings available at train time?

[ Parent | on HN ]

Re:Large language models are having their Stable Diffusion m... by freezed88 on Saturday March 11, 2023 @09:47PM (#35115911)

LlamaIndex offers ways to chunk up your data and store them in data structures for response synthesis: https://gpt-index.readthedocs.io/en/latest/guides/primer.htm...

[ Parent | on HN ]