top | item 45854136

(no title)

floodfx | 3 months ago

Why are completion tokens more with image prompts yet the text output was about the same?

discuss

order

cma|3 months ago

Some multimodal models may have a hidden captioning step that may take completion tokens, others work on a fully native representation, and some do both I think.

Garlef|3 months ago

"Thinking" Mode

nunodonato|3 months ago

it doesn't say that anywhere.