EASIEST Way to Fine-Tune LLAMA-3.2 and Run it in Ollama

แชร์
ฝัง
  • เผยแพร่เมื่อ 18 พ.ย. 2024

ความคิดเห็น • 48

  • @gramnegrod
    @gramnegrod หลายเดือนก่อน +2

    Great video. You make it look so easy! I’m really looking forward to the vision based rag. I’m hoping good vision models with vision rag will open up a lot of creative use cases.

    • @engineerprompt
      @engineerprompt  หลายเดือนก่อน

      Here are a couple of examples of vision based RAG:
      th-cam.com/video/w5WGbUGAE3s/w-d-xo.html
      th-cam.com/video/DI9Q60T_054/w-d-xo.html

  • @lulzkiller666
    @lulzkiller666 หลายเดือนก่อน +5

    Nice video. Could you please make a video on how to train it on "own" content. Lets say, i have the complete API documentation for an APP, i want to train it on this API documentation so that it can help me code faster with the correct API's. That would be awesome

  • @epokaixyz
    @epokaixyz หลายเดือนก่อน +12

    Consider this your cheat sheet for applying the video's advice:
    1. Research the different sizes of Llama 3.2 models.
    2. Download the Unsloth Fine-Tuning Notebook.
    3. Acquire the FineTome-100k dataset.
    4. Fine-tune a Llama 3.2 model with Unsloth, using LoRA adapters and prompt engineering.
    5. Create an Ollama model file for your fine-tuned model.
    6. Run your fine-tuned Llama 3.2 model locally with Ollama.
    7. Start building custom AI applications!

    • @Criminal_H4_ff
      @Criminal_H4_ff หลายเดือนก่อน

      Broo till step 6 i have completed but i cant run my finetunned model in ollama what should i do now 🤧

  • @tanguyvansnick3954
    @tanguyvansnick3954 3 วันที่ผ่านมา

    Great tutorial 🔥

  • @kunalr_ai
    @kunalr_ai หลายเดือนก่อน +12

    Here are the key points from the video:
    * Meta released a new family of four different models, including multimodal models, called LLaMA 3.2.
    * The models are impressive for both language and vision tasks for their respective sizes.
    * You can fine-tune LLaMA 3.2 for your own custom tasks.
    * You can use Unslot for fine-tuning and Ollama for running the fine-tuned model locally.
    * The 1 and 3 billion models are particularly interesting because you can run them on device.
    * Meta has also released LLaMA Stack, which is their opinionated version of how developer experience should look.
    * You can fine-tune one of the smaller models on your own data set and then run it locally using Ollama.
    * You will need to provide your own data set and follow the specific prompt template used by the model.
    * You can use the official notebook from the Unslot team to fine-tune LLaMA 3.2.
    * You can use the supervised fine tuning trainer from the TRL library to train the model.
    * You can save the trained model as a GGf file and then load it in Ollama.
    * You can create a model file in Ollama and then run the model using the AMA run command.
    Timeline with tags:
    00:00 - 00:15: Introduction
    00:15 - 02:00: Meta releases LLaMA 3.2
    02:00 - 04:00: LLaMA 3.2 models
    04:00 - 06:00: Fine-tuning LLaMA 3.2
    06:00 - 08:00: Unslot and Ollama
    08:00 - 10:00: 1 and 3 billion models
    10:00 - 12:00: LLaMA Stack
    12:00 - 14:00: Fine-tuning LLaMA 3.2 on your own data set
    14:00 - 16:00: Prompt template
    16:00 - 18:00: Unslot notebook
    18:00 - 20:00: Supervised fine tuning trainer
    20:00 - 22:00: Saving the trained model
    22:00 - 24:00: Running the model in Ollama

  • @rezcan
    @rezcan หลายเดือนก่อน

    Great video, thanks can you make a video to show how to fine tune Llama 3.2 90B vision model?

  • @AshwaniKumar-r4p
    @AshwaniKumar-r4p 3 วันที่ผ่านมา

    In the fine-tuning process demonstrated in the video, does the model primarily learn response patterns, or does it genuinely absorb and retain the specific knowledge contained in the training dataset?

  • @dipeshrathore8842
    @dipeshrathore8842 หลายเดือนก่อน +4

    Great video!
    Can you please create a video or guide demonstrating Fine-tuning of Llama 3.1 8B
    First on raw text (books, discourses etc.)
    Then on instruction dataset (less data 8-10k)?
    And what's best? 8B-base or 8B-instruct for this?! (I don't wanna lose general chat capabilities)

  • @tapikoBlends
    @tapikoBlends 3 วันที่ผ่านมา

    is it possible to make fine-tuning using text?(not structured in json format)
    text will be tomething like instruction

  • @Abhijit_SU
    @Abhijit_SU หลายเดือนก่อน +2

    I have used the same notebook to fine tune my model.
    I am getting an error saying "Keyerror: name" when i am trying to either push it to HF or saving it locally.
    After executing the GGUF / llama.cpp Conversion part it is running and then after 3 mins exact it is showing the error every time. Please tell me how did you manage to download the GGUF file locally using the same Notebook which You have provided. Please Help, Thanks In Advance !

    • @rickymorty8198
      @rickymorty8198 หลายเดือนก่อน

      Getting the same error too

    • @rickymorty8198
      @rickymorty8198 หลายเดือนก่อน

      Any solutions?

  • @raunaksharma8638
    @raunaksharma8638 หลายเดือนก่อน +1

    Can we use normal Alpaca type dataset with input , output and instruction here ?

  • @deschwedda
    @deschwedda หลายเดือนก่อน +9

    I want to exceed limitations and remove censorships. Is it possible, and how? thank you so much.

    • @Incredible_428
      @Incredible_428 หลายเดือนก่อน +3

      You need to fine-tune it with a dataset which contains uncensored chat data, it should be well mannered/structured so that the model will learn batter patterns

    • @deschwedda
      @deschwedda หลายเดือนก่อน +1

      @@Incredible_428 thank you, any dataset recommendations? (llama 3.2)

    • @engineerprompt
      @engineerprompt  หลายเดือนก่อน +6

      look for dolphin models, they are usually uncensored.

    • @deschwedda
      @deschwedda หลายเดือนก่อน

      @@engineerprompt thank you!

    • @tnix80
      @tnix80 หลายเดือนก่อน +1

      If you can jailbreak AI and the woke nonsense, a lot of people are going to want to use your jailbreaking technique/tool. I could see making a lot of money.

  • @lysanderAI
    @lysanderAI 24 วันที่ผ่านมา

    Could you do a video of finetuning using axolotl + unsloth

  • @HarshSingh-cp8mq
    @HarshSingh-cp8mq 14 วันที่ผ่านมา

    hey i want to build my personal assistant on the LLAMA3.2 and i want to assign a name to it. Also while asking the owner it tells me about meta this also i want to change?? Can anybody guide me

  • @MuhammadAsif-mm4py
    @MuhammadAsif-mm4py หลายเดือนก่อน

    Can i use this model in my android application? Please help

  • @edengate1
    @edengate1 หลายเดือนก่อน

    Which model is the best one to upload my files, books and documents to fine tune and training?

    • @randomswedishdude
      @randomswedishdude หลายเดือนก่อน +1

      You shouldn't. You fine tune for specific behaviour. Not to know your (changing) data. Just use RAG for your docs

    • @edengate1
      @edengate1 หลายเดือนก่อน

      @@randomswedishdude I want both, to get a truly assistant with the know of my behavior and all my data. But thanks, didnt know the difference

  • @Qwme5
    @Qwme5 หลายเดือนก่อน

    Can I finetune this llm with a new langauage like Arabic if so should I use the original tokenizer of llama 3.2.
    Another question , how much it will cost me on google colab to finetune such small model like 3B.

    • @avataraang3334
      @avataraang3334 หลายเดือนก่อน +1

      Nothing.. T4 gpu gives you around 1-3.5 hours of free resource.. thats plenty so smaller models

  • @sergiosilveramurcia4216
    @sergiosilveramurcia4216 หลายเดือนก่อน

    Has anyone tried to run it locally on MacOs, does it change the code substantially?

  • @annwang5530
    @annwang5530 หลายเดือนก่อน +1

    Can that gguf run locally on DAN or LMStudio?

    • @xmagcx1
      @xmagcx1 หลายเดือนก่อน

      x2

    • @engineerprompt
      @engineerprompt  หลายเดือนก่อน

      Yup, on almost anything you want, if its based on llamacpp.

    • @annwang5530
      @annwang5530 หลายเดือนก่อน

      @@engineerprompt do you take fine tune tasks? I got a Json dataset I fail to fine tune...

  • @yan_yan_1995
    @yan_yan_1995 หลายเดือนก่อน

    may i know the screen recording software he's using ? it's cute !

    • @engineerprompt
      @engineerprompt  หลายเดือนก่อน +1

      screen.studio :)

    • @yan_yan_1995
      @yan_yan_1995 หลายเดือนก่อน

      @@engineerprompt thank you !!!

  • @jackluka773
    @jackluka773 หลายเดือนก่อน +2

    why the heck it has to be so complicated? can't it be wrapped in some easy to use GUI with drop down list creator with description of the consequences for each choice?

    • @yufeixu4479
      @yufeixu4479 2 วันที่ผ่านมา

      You go program it then 😂 this is easy already... if you can't do it then don't do it and don't hate buddy

    • @equious8413
      @equious8413 วันที่ผ่านมา

      This is cutting edge computing science. Paint by numbers aint here yet.

  • @大支爺
    @大支爺 หลายเดือนก่อน

    Uncensored patch first!

  • @robertjalanda
    @robertjalanda หลายเดือนก่อน

    great video waiting for vision support

  • @Criminal_H4_ff
    @Criminal_H4_ff หลายเดือนก่อน

    Brother i got error while doing the command ollama run mymodelname it throws the error as ollama runner function terminated and vocabulary and tokenizer merges files are not found issue what should i do now will you please any contact of yours i need immediate help bruh😮‍💨🥲