Fine tuning Embeddings Model

Поділитися
Вставка
  • Опубліковано 1 жов 2024

КОМЕНТАРІ • 10

  • @thevadimb
    @thevadimb 3 місяці тому

    First, thank you for your video - I really appreciate your work!
    A question - I see the validation loss is actually growing... Am I missing some point here?

    • @moslehmahamud
      @moslehmahamud  3 місяці тому

      You are right, i didn’t properly train the model with sufficient data or necessary steps/epochs. Please don’t be like me hahaha
      Hope that answers your question

  • @ashleeclaral3271
    @ashleeclaral3271 3 місяці тому

    how should my own custom dataset look like?

    • @moslehmahamud
      @moslehmahamud  3 місяці тому

      you can try using pair-wise, labeled dataset to train the embeddings model

  • @wilfredomartel7781
    @wilfredomartel7781 4 місяці тому

    Great video! is it only for english?

    • @moslehmahamud
      @moslehmahamud  4 місяці тому +2

      Thanks, you can train on other languages too, make sure to pick a multi-lingual model.

  • @rahul01483
    @rahul01483 3 місяці тому

    do you have any video on how I can train my own dataset from scratch and create embedding vector store

    • @moslehmahamud
      @moslehmahamud  3 місяці тому +1

      yes, a new video will be uploaded tomorrow (as of writing), using hf model to get embeddings. You can use a chroma db to store the embeddings
      Hope that helps

    • @rahul01483
      @rahul01483 3 місяці тому

      @@moslehmahamud sure it helps, as have been using chromadb for some time now... would love to see ur impl

    • @tunguyet3615
      @tunguyet3615 2 місяці тому

      @@moslehmahamud where video?