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

Поделиться
HTML-код
  • Опубликовано: 28 янв 2025

Комментарии • 48

  • @PortfireStudios
    @PortfireStudios Месяц назад +3

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

  • @AmirAttari1
    @AmirAttari1 24 дня назад +1

    This video is like a hidden gem, Thanks Jason!

  •  Месяц назад +2

    Very useful. Thank you Jason.

  • @robertjalanda
    @robertjalanda Месяц назад +2

    Thanks for the video was waiting on this one😛

  • @PhilEhI
    @PhilEhI Месяц назад +2

    Fantastic job of teaching. Fast paced but great.

  • @karthikeya2853
    @karthikeya2853 Месяц назад +5

    🎯 Key points for quick navigation:
    00:00 *📈 Improvement in large language model fine-tuning, especially with new models like Llama 3.2, enhances options for AI developers.*
    01:11 *📚 Retrieval Augmented Generation (RAG) is simpler than fine-tuning for integrating private knowledge into models.*
    02:49 *⚖️ RAG allows easier updating of knowledge bases, while fine-tuning locks model knowledge based on training data.*
    04:40 *💡 Choose RAG for basic knowledge integration, but fine-tune for specialized tasks or behaviors.*
    05:22 *🔄 Proper data preparation is crucial for successful fine-tuning, with various data sourcing methods available.*
    06:59 *🎤 Assembly AI provides accurate transcription services, enhancing the data preparation process for fine-tuning.*
    09:33 *🧬 Synthetic data generation can be utilized to create training datasets for specific tasks efficiently.*
    10:01 *⚙️ Close-source vs. open-source models: Understand the trade-offs in control, cost, and ease of use during fine-tuning.*
    14:11 *🔑 When selecting a base model, consider cost, speed, and the specificity of your use case for optimal performance.*
    16:43 *📝 Fine-tuning methods: Full fine-tuning vs. LoRA, with the latter being more efficient and suitable for many applications.*
    18:21 *🚀 Using Unsought can drastically reduce memory usage and increase speed in the fine-tuning process on consumer-grade GPUs.*
    20:14 *🎯 Focus on training the lag and target modules for optimal model fine-tuning.*
    20:28 *⚖️ Finding the right balance for the learning rate is crucial; too high can cause overfitting, while too low may not yield significant changes.*
    20:57 *📊 Data preparation involves converting prompts into model-specific syntax using a feature from unsloth called standardized share GPT.*
    22:24 *🚀 The fine-tuning process can be efficiently executed using the FFT trainer from Hugging Face, focusing on assistant outputs.*
    23:21 *📈 If results aren't satisfactory, consider providing more training data or switching to a larger model for better reasoning.*
    24:03 *💾 You can export either the small adapter file or the larger GGF file for deployment, including access to Hugging Face.*
    24:30 *🤝 Join the AI Builder club for deeper insights on fine-tuning, deploying models, and collaborating with experienced AI builders.*
    Made with HARPA AI

  • @prometheas
    @prometheas 21 час назад

    Man. This video fucking crushes it. First one if yours I’ve seen and subscribed 3/4 way through. Keep it up 🔥

  • @AITitus
    @AITitus Месяц назад +2

    Awesome work!!

  • @Dron008
    @Dron008 Месяц назад +2

    What a nice tutorial. Thank you, it was very useful. At last I am starting to understand something. Great educational work.

  • @iamxenobyte
    @iamxenobyte 22 дня назад

    Good stuff dude

  • @alourbright1835
    @alourbright1835 Месяц назад +11

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

  • @zandanshah
    @zandanshah 2 дня назад

    well done. Good information

  • @bronxandbrenx
    @bronxandbrenx Месяц назад +1

    Eggxellent Master.

  • @vt7637
    @vt7637 Месяц назад +25

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

    • @yijin241
      @yijin241 Месяц назад +3

      Those who introduce fine-tuning on RUclips 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 Месяц назад +3

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

    • @reserseAI
      @reserseAI Месяц назад +1

      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 Месяц назад +1

      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 Месяц назад

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

  • @shresthsamyak2686
    @shresthsamyak2686 Месяц назад +2

    can ya show how to deploy with llama?

  • @Rexschwert
    @Rexschwert 23 дня назад

    I may sound dumb af, but how is that possible (8:13)?
    Is it Python or some JSON extension? If an extension, which one? And if not, in what format should it be done? It's not very convenient to separate CoT or formatted text from each other with a
    separator. Or is it not necessary to take syntax errors into account at all?

    • @A_Concerned_Citizen
      @A_Concerned_Citizen 18 дней назад +1

      lol it’s shit like this that makes my shit explode watching these ai dudes

  • @JR-joren
    @JR-joren Месяц назад +1

    hey jason, i've been following you for a while now, and was wondering if your community is beginner friendly or do we need t have some coding notion? thanks.

  • @skanderhariati8814
    @skanderhariati8814 Месяц назад

    I believe unsloth doesnt currently support training or inference on 8bit quantized models although it allows u to load it.

  • @skanderbegvictor6487
    @skanderbegvictor6487 Месяц назад

    I kind of disagree with book example for LoRa. Full finetuning can also be considered as writing parts of book to tailor to your use case

  • @hailynewma9122
    @hailynewma9122 16 дней назад +1

    computer specs?

  • @readmarketings9061
    @readmarketings9061 Месяц назад +1

    wow

  • @Kevencebazile
    @Kevencebazile Месяц назад +1

    Nice work jason. I am reviewing your content. Would love to pair program and work together. #devgang

  • @UkutaFeni
    @UkutaFeni 24 дня назад +1

    just feedback! I think you talk too much especially in the beginning which is hard to listen especially the fact that we didn't get any value yet and we get bombarded with just yap. and with you accent its even harder.

  • @IsxaaqAcademy
    @IsxaaqAcademy Месяц назад +2

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

    • @10xApe
      @10xApe Месяц назад

      What do you mean by that ?

    • @RedSky8
      @RedSky8 Месяц назад +1

      @@10xApe I will say that I've tried to use unsloth myself locally and it didn't work. I tried it so many ways and asked questions on their discord but nothing worked. That was about 4 months ago though so maybe they actually made things easier......maybe.

    • @danielhanchen
      @danielhanchen Месяц назад +3

      ​@@RedSky8 Hey Unsloth founder here - what was the error you experienced? FYI we now allow pip install Unsloth which might help with the process.
      Currently Unsloth does not work on Windows (unless you use WSL2) or Apple but it's coming soon!

    • @skanderhariati8814
      @skanderhariati8814 Месяц назад

      @@danielhanchen is there a way to use 8bit quantized model for inference while using unsloth library, we can load the model in 8 bit by sett load_8bit = true and load_4bit = false, but issue will arise when trying to use the model for inference as it will be there a mismatch in dtype "c10::BFloat16 != signed char"

  • @michealhall7776
    @michealhall7776 Месяц назад +1

    Focus more on the content, not revenue. Your videos are sometimes good, and sometimes lacking any substance, just space to fill before a advert.

    • @sohaib07
      @sohaib07 Месяц назад +3

      What are you bringing to the table, stop dissing.

  • @Truzian
    @Truzian Месяц назад

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