mirror of
https://github.com/mudler/LocalAI.git
synced 2025-06-29 22:20:43 +00:00
![]() Instead of just summing the components to see if they equal 1.0, take the actual magnitude/p-norm of the vector and check that is approximately 1.0. Note that this shouldn't change the order of results except in edge cases if I am too lax with the precision of the equality comparison. However it should improve performance for normalized vectors which were being misclassified. Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
---|---|---|
.. | ||
bark | ||
image | ||
llm | ||
stores | ||
transcribe/whisper | ||
tts | ||
vad/silero |