EASIEST Way to Train LLM Train w/ unsloth (2x faster with 70% less GPU memory required)

Поділитися
Вставка
  • Опубліковано 16 гру 2024

КОМЕНТАРІ • 17

  • @PortfireStudios
    @PortfireStudios 17 годин тому +2

    Nice work Jason. I appreciate the pace. Keep up the good work!

  • @philpilkington
    @philpilkington 19 годин тому +2

    Fantastic job of teaching. Fast paced but great.

  • @robertjalanda
    @robertjalanda 19 годин тому

    Thanks for the video was waiting on this one😛

  • @alourbright1835
    @alourbright1835 День тому +3

    Hello Jason, could you kindly add the code so that we can follow along.

  • @vt7637
    @vt7637 День тому +6

    You gotta tell us how we can fine-tune an open source model on a non-public PDF. Everybody on UA-cam uses hugging face toy datasets for fine-tuning that is basically useless.

    • @yijin241
      @yijin241 День тому +2

      Those who introduce fine-tuning on UA-cam they definitely know they are just talking nonsense.Even OpenAI and Claude they don't know how to leverage RLHF to solve the real case.for example even you used RLHF for stock trading you definitely will lose your pants!

    • @Pregidth
      @Pregidth День тому +1

      Agree. Creating a dataset with sensible data in the cloud makes everything obsolete. But anyhow good explanation!

    • @ibrahims5636
      @ibrahims5636 21 годину тому

      I use script to make qna using open ai api all my pdf data into csv format, then convert my csv as jsonl for fine tune then make another version into json to upload it to vector database rag purpose, then fine tune gpt4o mini base model, still not give me good result 😅

    • @robertjalanda
      @robertjalanda 19 годин тому

      There are hundreds of new public datasets released on Hugging Face per week and they all work for finetuning. Also if you want it for your specific usecase, everything requires some sort of custom data - e.g. RAG needs a database.

    • @robertjalanda
      @robertjalanda 19 годин тому

      ​@@yijin241Finetuning works great, if you know what you are doing.

  • @readmarketings9061
    @readmarketings9061 День тому +1

    wow

  • @IsxaaqAcademy
    @IsxaaqAcademy 9 годин тому

    The problem with these misleading videos is that they provide partial information

  • @Truzian
    @Truzian 23 години тому

    Why are you shilling every video? I can no longer trust the tools you recommend