EASIEST Way to Fine-Tune a LLM and Use It With Ollama

Поділитися
Вставка
  • Опубліковано 24 лис 2024

КОМЕНТАРІ • 126

  • @warpdotdev
    @warpdotdev  2 місяці тому +14

    What data would you fine tune your LLM on?

    • @siaboonleong
      @siaboonleong 2 місяці тому +2

      what is your hardware ? are you using intel or amd threadripper ?

    • @themax2go
      @themax2go 2 місяці тому

      that depends on the use case... are you asking for what use cases people are aiming to support?

    • @themax2go
      @themax2go 2 місяці тому

      but i guess here's one: finetuning qwen2.5-32b on various ai related github prjs that are written in python, with a focus on agentic workflows, maybe individual finetunes for each agent python lib / framework, such as autogen, langchain / langgraph, ...

    • @shiftto
      @shiftto Місяць тому

      youtube need more chanels alike this. great job

    • @Toti330
      @Toti330 Місяць тому +2

      I'm using it to fine-tune a Minecraft bot (Mindcraft from Emergent garden)

  • @siddhubhai2508
    @siddhubhai2508 2 місяці тому +125

    No over rating, no over talking, streight forward, love it.

    • @OilersFlash
      @OilersFlash Місяць тому +1

      Sadly this may be the first time I disagree with that sentiment. Haha. I loved it but was looking for a course link at the end because it was too much too fast ;)

    • @siddhubhai2508
      @siddhubhai2508 Місяць тому +3

      @@OilersFlash Yea bro (actually uncle, cuz I'm 15 and your dp shows...), I realized that the viewer will need some pre knowledge of LLMs and its workings and also some pre basic knowledge of fine-tuning! But yea the video was good actually!

    • @OilersFlash
      @OilersFlash Місяць тому

      @@siddhubhai2508 it is good ;)

  • @injeranamitmita
    @injeranamitmita 11 днів тому +2

    Knowing such a deep technical subject is one thing, but teaching it well is another! well done young lady.

  • @cjofre
    @cjofre 2 місяці тому +27

    This is exactly how we are tuning our open source LLMs, the use of unsloth+LORA is key. Validation of the learning is an adventure. We did this over the same tech stack mentioned here. Very good video, of course, lots of details behind each step that cannot be explained in a short video. Great use of lighting and your pace is excellent. Looking forward to more vids.

  • @Emocar2
    @Emocar2 Місяць тому +13

    Thank you straight to the point
    I usually have some ptsd when looking at tutorials

    • @thecaptain2000
      @thecaptain2000 Місяць тому

      it depends, this is useful, just if you already know how to do it and you just need a refresh on the steps. In other words, you want to watch it just if you do not need it

  • @first-thoughtgiver-of-will2456
    @first-thoughtgiver-of-will2456 2 місяці тому +7

    Great video for people who know coding and local llm but havent finetuned!

  • @Laowater
    @Laowater 25 днів тому +2

    amazing quality of editing, sound, video - beyond the programming side!
    A pleasure for the eyes and ears to watch!

  • @arianetrek7049
    @arianetrek7049 Місяць тому

    I was already taken by the clear content but the KEY highlight of simply mentioning Conda shows the high quality of your informations. Subscribed and thanks for the tuto.

  • @sommerliermovie3547
    @sommerliermovie3547 Місяць тому +1

    This is what I am thinking to do. Finding this video maybe saved half a day

  • @ToastyWalrus7
    @ToastyWalrus7 26 днів тому

    Easiest subscribe of my life, just wanted something easy and straight to the point

  • @frobledo5584
    @frobledo5584 Місяць тому +1

    Insanely good video!! Straight to the point and great presentation

  • @foju9365
    @foju9365 2 місяці тому +2

    Five minutes made useful. Thank you for the crisp and neat video. ❤

  • @valenciawalker6498
    @valenciawalker6498 19 днів тому

    Great explanation and presentation of LLM.

  • @mr.gk5
    @mr.gk5 Місяць тому +7

    Great video straight to the point, but could you please elaborate more on feeding custom dataset to the script? What are the steps? You wrote it right on the script or did you load it from a different file? Or did you upload to hugginface and use the token from there? Im confused

  • @lakshman587
    @lakshman587 15 днів тому

    Intresting video!!

  • @AghaKhan9
    @AghaKhan9 2 місяці тому +7

    Hi there.
    It's wonderful.. Will you Please share the notebook and also Google Collab notebook?

  • @HellTriX
    @HellTriX Місяць тому +12

    Every how-to I've found so far glazes over the training datasets. Like here she goes from here is 100k sql dataset, then here are is how the model expects the prompt, but then doesn't show the format of how the dataset is loaded into the model. What does the sql_context look like, what does the sql_prompt look like, what is the sql, and sql_explaination? Fine tuning is one thing but people also need to know how to build and integrate datasets for training.

    • @twistyx808
      @twistyx808 День тому +1

      Agreed. Every video is skipping over detail to actually build your own functionality.

    • @jofus521
      @jofus521 День тому

      That’s kind of the point. It’s open source open secret

  • @chokosabe
    @chokosabe Місяць тому

    What a clean presentation.

  • @robertjalanda
    @robertjalanda 2 місяці тому

    great and short video guys incredible!!

  • @adrainhuang6068
    @adrainhuang6068 23 дні тому

    good guide to play by myself

  • @Larimuss
    @Larimuss Місяць тому +1

    Great tutorial! Thanks. Really like the definitions and explanations rather than just glossing over the code.. would love to see a full tutorial series 😮
    I'd like to try to code it myself, but it would be good if you could share the code too.

  • @BCRBCRBCRBCRBCRBCR
    @BCRBCRBCRBCRBCRBCR Місяць тому

    Appreciate the brevity. Thank you.

  • @anandraj2895
    @anandraj2895 2 місяці тому

    nice and straight forward approach

  • @nagalman
    @nagalman Місяць тому

    Great video. To the point. Effective

  • @elasdebastos235
    @elasdebastos235 2 місяці тому

    I actually liked the music. Great editing also. I found the proyect idea a little bit boring. You could train it for something actually awesome

  • @flutterflowexpert
    @flutterflowexpert Місяць тому

    Great video! Subscribed! 🎉

  • @markring40
    @markring40 2 місяці тому

    Another great video!! Thanks.

  • @jason77nhri
    @jason77nhri 3 дні тому

    Thank you for your informative tutorial.
    I’ve installed Ollama on Windows 10 and currently only use it for interactive conversations through CMD.
    However, I asked a friend, and they mentioned that Ollama cannot be used for fine-tuning. Why is that?
    Additionally, Unsloth offers convenient online fine-tuning, but if the training data requires privacy and fine-tuning needs to be done locally
    or even if the base model is in Safetensors format from others-where should I start?
    Are there any learning resources or references you would recommend?
    Thank you!

  • @Hey.MangoJango
    @Hey.MangoJango 2 місяці тому +1

    Well explained. Thanks

  • @sreeramn5240
    @sreeramn5240 26 днів тому

    Thanks 🙏

  • @0xngmi
    @0xngmi 2 місяці тому +5

    wouldve been nice if you had shared the full collab code...

  • @nnpy
    @nnpy Місяць тому +1

    Yoo, what theme are you using in your system?? That's really cool

  • @rtATvw
    @rtATvw 3 дні тому

    @warpdotdev
    In the interest of establishing the repeatability of your result can you indicate whether the output @ 5:01 is unedited? typical? Mine is amending the prompt and typically produces output in the format of the Alpaca training text generating entries of 'SQL Prompt', 'SQL', 'Explanation', 'Question', 'Instruction', 'Company database' in the output.

  • @hansgruber3495
    @hansgruber3495 9 днів тому +1

    Nice video, but the music is way too disctracting.

  • @AIinAgriculture
    @AIinAgriculture Місяць тому

    Thank you for video. I followed your approach for finetuning the model text to SQL. When I work on my own database, its performance is not good. Unable to generate SQL query. I even used agent and examples queries our database. I am requesting suggestion from you. Thank you

  • @AnirbanKar4294
    @AnirbanKar4294 Місяць тому

    subscribed

  • @TheMariolino2005
    @TheMariolino2005 2 місяці тому

    Excellent direct video on fine-tuning, congrats. Could you also share the python source code that you used in the video? Thanks.

  • @bnug242
    @bnug242 День тому

    is the notebook posted anywhere?

  • @BrentLeVasseur
    @BrentLeVasseur 2 місяці тому

    Excellent tutorial! Doesn’t lowering the bit depth of the model greatly reduce accuracy? What are the pros and cons of doing so? Thanks!

  • @magnusjensen2767
    @magnusjensen2767 4 дні тому

    I would appreciate if this tutorial went more into detail on how to make a dataset comply with the model's promt template. From this video, there is no data processing being done and i think in real cases you would have to work with the data, or write a script, that chnges the data so that it fits with the prompt template (e.g. the Alpaca one she shows in the video)

  • @telepathytoday
    @telepathytoday 2 місяці тому

    How long did it take for the training / fine-tuning on your 4090? Thanks for the video!

  • @WolfsKonig
    @WolfsKonig Місяць тому

    Nice

  • @MuhammadFahreza
    @MuhammadFahreza 2 місяці тому

    what ubuntu are you using, the terminal looks dope

  • @oloix
    @oloix 12 днів тому

    Thanks! Although I do have a question why you show so much of yourself... I admit it's nice and pleasant to look at, however I would prefer to look at the code or things you talk about. Especially when I watch your videos at work I would definitely like to avoid someone thinking that I watch some silly videos during work while I actually watch work related stuff. Anyway, really interesting videos so thanks again! 😊✌

  • @sikandarali5117
    @sikandarali5117 2 місяці тому +1

    I'm working on a RAG application. I'm using a pdf file as a text data and I have clean the data as well using NLTK. I already have ollama install in my local system and also llama2 model. I
    embed the data in to vector form using ollama embedded model mxbai-embed-large and store it on chromabd. but if I give the prompt and get response, it give me the response but not according to my data. and how do I finetune the model? I just need guidance and sequence so I work on the project. It's important to me. I need your guidance. please reply. I'm using windows10.
    Thank you!

    • @ibrahimgamal7603
      @ibrahimgamal7603 Місяць тому

      It's easy you should write in your prompt template = """Answer the question based ONLY on the following context:
      {context}
      Question: {question}
      """

    • @muhammadumarnawaz9200
      @muhammadumarnawaz9200 Місяць тому

      @@ibrahimgamal7603 Could be anything such as you are not using a good doc extractor or your embedding model sucks. Changing chunk and overlap size might help. Don't go for finetuning straight away, do some experimentation and figure out where the problem lies exactly otherwise even finetuning won't work.

    • @sikandarali5117
      @sikandarali5117 Місяць тому

      @@muhammadumarnawaz9200 ok mate thank you for your help

  • @alucard00mx
    @alucard00mx Місяць тому

    It was a great video, but I have a question, is it compatible with the new versions called 3.2, especially versions 1B and 3B?

  • @Kappaツ
    @Kappaツ 21 день тому +1

    damn, now i want to create my own personal DAN assistant without OpenAI interfere with her

  • @DabnisUK
    @DabnisUK Місяць тому

    Apologies if this is a dumb question, but where is, is there a link to the notebook?

  • @lesptitsoiseaux
    @lesptitsoiseaux Місяць тому

    I have 55K classes with an ungodly amount of transcripts. What'll be better and faster? RAG or finetuning?

  • @4.0.4
    @4.0.4 2 місяці тому

    Can you train 12B on 24GB or is 12B too big?
    Another question is if you have multi-turn data (conversations) can you finetune on that? The examples I see are for Q:A pairs.

  • @diasdeinvierno8041
    @diasdeinvierno8041 2 місяці тому +1

    It's a great how to but you missed a "before trainng" and "after training" examples of how the model responded. Good video anyway. Couldn't get much out of it though

  • @furetosan
    @furetosan 24 дні тому

    Isn't this RAG? Doesn't chunking fit anywhere?

  • @elleryfamilia8291
    @elleryfamilia8291 Місяць тому

    if I train a model, will the responses be restricted to just my training data/examples? Or does the model's original training also play a role?
    For example, say I trained it on model to respond with vehicle specs. I feed it a vehicle name and the model returns the vehicle specs. Say I finetune the model with 50 examples (honda civic, toyota camry, volvo xc90, etc).... however, in reality there are 300,000 possible vehicles. Would finetuning on 50 examples help? Sure, I can put the 50 models in the prompt but then I'd just be wasting tokens.

  • @anshvashisht8519
    @anshvashisht8519 11 днів тому

    where is the link for google colab?

  • @noachere
    @noachere Місяць тому

    Do you have github repo of the code?

  • @PMe-my1td
    @PMe-my1td Місяць тому

    can this be done all from the wsl terminal? I am using ollama, webui and docker, but would like to train some company pdf's better, can this be done?

  • @IvanLesnov
    @IvanLesnov Місяць тому +1

    fine tuneing offline ?

  • @GARYGUS
    @GARYGUS Місяць тому

    what is the estimate cost for training such a model?

  • @isbestlizard
    @isbestlizard 5 днів тому

    I think I'll just get an llm to make the dataset and make it llms both sides of the data->training loop

  • @programan6391
    @programan6391 2 місяці тому

    Does fine-tuning shouldn't generate small models that theoretically run fully local and avoid spending money on OpenAI?

  • @infotainment6830
    @infotainment6830 20 днів тому

    Is it possible to make your own AI model with this that speaks to you like Jarvis and understands tone, etc?

  • @imai_official
    @imai_official Місяць тому

    How to collect dataset pls show it

  • @maloyaircraft1174
    @maloyaircraft1174 Місяць тому

    Video on formatting data sets to follow? 😅

  • @WiteBot
    @WiteBot 2 місяці тому

    Give us the collab link! Or better yet the llamasql gguf link!

  • @shashanksinghal8395
    @shashanksinghal8395 2 місяці тому +1

    why didn't you directly use hugginface trainer to train, why using unsloth? I want to know what was the benefit of using unsloth over hugginface trainer.

    • @Frxnb
      @Frxnb 2 місяці тому

      No benefit My friend :(

    • @andrescmarin
      @andrescmarin 2 дні тому

      Less memory was what she stated

  • @Hypotaksen
    @Hypotaksen 2 місяці тому +1

    Here it is, she says.. For simplicity.... A pip install command.. In a video.. With no pasted text to copy in the description.
    That's the opposite of simplicity.

  • @eduardmart1237
    @eduardmart1237 2 місяці тому +1

    Is unsloath free?

  • @catarctic
    @catarctic 2 місяці тому +2

    Congrats for finding such a smartie-cutie as a DevRel for Warp

  • @benjaminbirdsey3281
    @benjaminbirdsey3281 Місяць тому

    Unsloth has a dependency of triton, which doesn't seem to be compatible with windows.

  • @hasanaqeelabd-alabbas3180
    @hasanaqeelabd-alabbas3180 3 дні тому

    Inam finding difficulty understanding the converting of data set

    • @hasanaqeelabd-alabbas3180
      @hasanaqeelabd-alabbas3180 3 дні тому

      Is ubuntu on windows ? Or dependent system ?
      I need more tiny steps to convert the dataset

  • @skants8276
    @skants8276 Місяць тому +1

    She's cute and I can now fine tune my llama 3. Yay 🎉

  • @RenikindiHanuth
    @RenikindiHanuth 2 місяці тому

    Thankyou sis

  • @DaveAlexKD
    @DaveAlexKD Місяць тому +1

    at 2:00 is 8 Billion not 8 bit.

  • @themohtab
    @themohtab 2 місяці тому

    We need a video to explain this video

  • @Hey.MangoJango
    @Hey.MangoJango 2 місяці тому +2

    Can we train tinyllama to do something similar? Since was trying to run AI on Raspberry Pi 5 (with Hailo AI Accelerator)

  • @danyahsan3958
    @danyahsan3958 26 днів тому

    link

  • @blackstonesoftware7074
    @blackstonesoftware7074 2 місяці тому +1

    Can I do this without Conda? I hate Conda

  • @proxyme3628
    @proxyme3628 28 днів тому

    Why not share the source code???

  • @bugsbane
    @bugsbane 5 днів тому

    that subselect that it generated @5:01 makes me instinctively cringe - hoping it would generate the subselect as a join... - for instance why do:
    "select p.* from posts as p inner join posttags as pt on p.post_id = pt.post_id where tag_id in ( select tag_id from tags where name = 'terminal' )"
    instead of:
    select p.* from posts p inner join posttags pt on p.post_i = pt.post_id inner join tags t on t.tag_id = pt.tag_id where t.name = 'terminal'
    seriously - the 2nd one appears easier to optimize. right? oh well....

  • @iTube4U
    @iTube4U 27 днів тому

    Ashley, look at me

  • @GaryLee-j2v
    @GaryLee-j2v 2 місяці тому

    Gonzalez Susan Walker Larry Martinez Joseph

  • @bebetter7388
    @bebetter7388 2 місяці тому

    cant use claude!!!!

  • @SandraGarcia-t1k
    @SandraGarcia-t1k 2 місяці тому

    Rodriguez John Thomas Lisa Rodriguez Jose

  • @atrocitus777
    @atrocitus777 2 місяці тому

    let us use ollama with warp ai :(

  • @mr_pip_
    @mr_pip_ 21 день тому

    Why are there so many videos that are useless as tutorials and give the impression that they are only about self-promotion? Seriously, anyone who understands this quick run-through here doesn't need any more tutorials, and for the vast majority of the rest, it's probably pretty useless.

  • @orphica5739
    @orphica5739 Місяць тому

    Good video, but it’s hard to imagine that you you actually sat there and edited out every breath and pause so that the whole video would sound like one massive run on sentence, only to shave off some 20 or 30 seconds of duration.

  • @sutharjay1
    @sutharjay1 Місяць тому +1

    Windows 🥴

  • @SaddamBinSyed
    @SaddamBinSyed 2 місяці тому +2

    Next time pls avoid the background music , it's distracting from focusing.

  • @elgodric
    @elgodric Місяць тому

    Are you a Mr or a Mrs? It's 202024 I don't wanna assume

  • @BeastModeDR614
    @BeastModeDR614 Місяць тому

    I want to create on that creates computer virus, and hacking software would it be the same idea? lol jk

  • @twinnoverse
    @twinnoverse Місяць тому +1

    wow to much stuf in 5min

  • @w2385-i2s
    @w2385-i2s 15 днів тому +1

    Obama use Ollama

  • @maskedcoder2005
    @maskedcoder2005 2 місяці тому

    Please bring it for windowsssssss😢😢😢

  • @samukarbrj
    @samukarbrj 2 місяці тому

    shes pretty... what was this video about?

  • @Brainwork66
    @Brainwork66 Місяць тому

    This video is not recommended for the newcomers. She speak fast, in every few second is a cut on the footage. Really not detailed

  • @rider2731
    @rider2731 Місяць тому

    You are so pretty.

  • @BarbaraYoung-n5q
    @BarbaraYoung-n5q 2 місяці тому

    White Donald Allen Deborah Anderson Kimberly

  • @samanthasaurya
    @samanthasaurya 14 днів тому

    Why she looks like Andrew Ng 😂😂

  • @livinagoodlife
    @livinagoodlife Місяць тому

    please talk to the lens and not yourself on the screen you're looking at

  • @themax2go
    @themax2go 2 місяці тому

    uv > anaconda