Tuning Your AI Model to Reduce Hallucinations

Поділитися
Вставка
  • Опубліковано 21 гру 2024

КОМЕНТАРІ • 9

  • @mehmetaliozer2403
    @mehmetaliozer2403 10 місяців тому +2

    3:28 how the temperature in high value could lead greedy results, while it is normalizing the selection chance and lead to get more random creative results than greedy (highest possible one)

    • @j.k.priyadharshini9753
      @j.k.priyadharshini9753 7 місяців тому

      as far as i know, temperature 0 makes the model to be more deterministic and repeatative. In many documents i have read that temp 1 leads to creative answer. can you provide links that supports you theory?

  • @quocthinhluu4098
    @quocthinhluu4098 10 місяців тому +8

    After tuning much enough, you realize the only thing that had been hallucinating all the time was yourself

  • @TOMESHTI
    @TOMESHTI 10 місяців тому +1

    Thanks for info
    Need to test.

  • @whathuh6965
    @whathuh6965 Місяць тому +2

    Why make a video about this topic and yet not exemplify your points by demonstrating them on an actual LLM in real time? (It's just babble if it doesn't contain proof).

  • @Rm-no6jr
    @Rm-no6jr 10 місяців тому +1

    You are the best

  • @Hshjshshjsj72727
    @Hshjshshjsj72727 10 місяців тому +1

    Please voiceover into English