LLAMA-2 🦙: EASIET WAY To FINE-TUNE ON YOUR DATA 🙌

Поделиться
HTML-код
  • Опубликовано: 22 дек 2024

Комментарии • 230

  • @teleprint-me
    @teleprint-me Год назад +51

    I was in the hospital because my lung collapsed and I've been having a seriously rough go at it lately (life long issues with fam, etc), so I really appreciate this video. Thanks for all your hard work. Researching these topics and understanding them is no small feat. Keep it up.

    • @engineerprompt
      @engineerprompt  Год назад +13

      I am really sorry to hear that! Hope you are recovering well. Wishing you a quick recovery. Also really appreciate all your contributions. Stay strong my friend!

    • @immortalsun
      @immortalsun Год назад +1

      Hope you get better!

  • @LainRacing
    @LainRacing Год назад +60

    Very disappointed you didn't show this actually doing anything. How to verify or test if its working. I can run a script and have it do nothing... How do we see it actually worked or test it.

  • @samcavalera9489
    @samcavalera9489 Год назад +14

    Thanks SO MUCH brother! You are a true hero! Fine tuning is the most important part of OS llms. That's where the value/wealth is hidden. I cannot wait for your following fine-tuning video.🙏🙏

  • @christianmboula8923
    @christianmboula8923 8 месяцев назад +1

    Superb tutorial by its clarity, simplicity and to the point...big Thank you! NOTE Bugfix : replace the underscore with corresponding dash to make the autotrain command run on colab

  • @karthigeyan88
    @karthigeyan88 Год назад +34

    Hi, thanks for the video, could you explain in detail how to load the model and create an inference api in the local machine? that would be really helpful. thanks in advance

    • @MuhammadFhadli
      @MuhammadFhadli Год назад

      hi, have you find a way to do the inference?

    • @karthigeyan88
      @karthigeyan88 Год назад

      @@MuhammadFhadli yeah, we have provisioned a Nvidia 64GB GPU machine and created an inference pipeline with llama.cpp library. Using an GGML model versiom from TheBloke huggingface

    • @immortalsun
      @immortalsun Год назад +1

      ‘Could you explain in detail […]’
      Talking to him like he’s ChatGPT

  • @jersainpasaran1931
    @jersainpasaran1931 Год назад +3

    Thank you very much champion! We are getting to the true spirit of open source, allowing science to be truly scalable for the public and public interests.

  • @arjunv7055
    @arjunv7055 Год назад +4

    One of the best video I have come across. I will definitely share this channel with my colleagues and friends who wants to learn more on this topic.

  • @photojeremy
    @photojeremy Год назад +25

    would be great to have a colab notebook for this that included inference on the finished pushed model

    • @MuhammadFhadli
      @MuhammadFhadli Год назад

      hi, have you find a way to do the inference?

    • @manujmalik9843
      @manujmalik9843 Год назад

      @@MuhammadFhadli did you find it?

    • @gerardorosiles8918
      @gerardorosiles8918 Год назад

      I was thinking that once you push to huggingface you could use something like text generarion webui to play with the model

  • @garyhuntress6871
    @garyhuntress6871 Год назад +2

    I was initially skeptical but this was an excellent short tutorial. Thanks!

  • @PickleYard
    @PickleYard Год назад +4

    Wow, just what I needed. I just put together a Flan Orca style dataset, I cant wait to try in Colab! Thank you for your hard work.

  • @bagamanocnon
    @bagamanocnon Год назад +2

    how can i incorporate my own data into the 'assistant' fine tune? for example, a 100 page document about a company product. do i format it into the something similar to what's in the openassistant dataset and add it to the dataset? or finetuning on own data will be another finetuning step? i.e. after finetuning on the openassistant dataset, i need to run another finetune for my own data? cheers and thanks for all your hardwork to share your knowledge to us!

  • @bardaiart
    @bardaiart Год назад +3

    Thank you very much!
    Looking forward to the dataset preparation video :)

  • @lallaaichakone2106
    @lallaaichakone2106 Год назад

    wooow, after days of seraching for videos. I see everything that i wanted in this video and in simple terms. Great work

  • @anjakuzev592
    @anjakuzev592 Год назад +7

    Please make a video for creating your own dataset and actually using the model

  • @Yash-mk8tc
    @Yash-mk8tc Год назад +5

    how to use this trained model?
    can you please make video on this?

  • @VerdonTrigance
    @VerdonTrigance 10 месяцев назад +1

    How to train on unstructured data (a book for example) with self-supervized train algorythm and eventually make a chat from it?

  • @zhirongchen9861
    @zhirongchen9861 Год назад +3

    Hi, how can I choose a method to finetune the model. For example, if I want to use LoRA to finetune lamma2, how can I do it?

  • @OpenAITutor
    @OpenAITutor Год назад +3

    So great! Thank you for being so clear!!! loving it

  • @dr.aravindacvnmamit3770
    @dr.aravindacvnmamit3770 10 месяцев назад

    Hi, the way you are explaining is very positive !!!! One solution am not getting is If I want to train my custom data on regional languages how to proceed can you share your knowledge on this. Which model is best on this and if we pass the Prompt in English will it gets converted to regional language and generates the ouput?

  • @Guggs-w6j
    @Guggs-w6j Год назад +2

    Can you make a video on fine tuning a llm model on a recipe dataset.

  • @serenditymuse
    @serenditymuse Год назад +2

    The major work looks to be in making your dataset properly. Which is pretty common. Do you have or are you planning another video that is for training models simply by handing it a lot of files of say web content or better still the raw urls and perhaps something like tags and such? In other words how to add to unsupervised learning from a corpus.

  • @8eck
    @8eck Год назад +4

    What if i only want to feed a specific non-instruction data into the model? For example some financial data or some books or some glossary? Can i just keep the ###Output empty, will the model learn from that data? Also, do i need to split that data into train and test parts or it is not required and is optional for pre-trained models?

    • @curtisho5255
      @curtisho5255 Год назад

      i have the exact same question! omg!

    • @phoenixfire6559
      @phoenixfire6559 Год назад

      If you leave the output empty then the model will learn to give you empty responses every time you put that type of data in. The best way to make the data for your finetune is thing about it from reverse. When you put the input in, what do expect the output to be? That's what you should be filling output with.

    • @8eck
      @8eck Год назад +2

      @@phoenixfire6559 i'm talking about pre-training like fine-tuning, models in the pre-training phase doesn't get any output examples, they just learn from the data, that's what i'm trying to understand. Is fine-tuning is only about question & answer pairs? How to continue pre-training of the model with frozen base weights. Just like transfer learning.

    • @curtisho5255
      @curtisho5255 Год назад +1

      @@8eck exactly. he don't get it. We want it to train on pure data, not train on Q&A responses. He must have not played with chatbase.

    • @robosergTV
      @robosergTV Год назад

      @@curtisho5255 lmao the author of the video knows this. The video is clickbait for farm views (which is money) from noobs, who cant use simple google search.

  • @jongheebae6269
    @jongheebae6269 11 месяцев назад +2

    I have the autotrain error as follows.
    autotrain [] llm: error: the following arguments are required: - -project-name
    So I changed '--project-name' instead of '--project_name'. Then faced another error.

  • @sharadpatel107
    @sharadpatel107 Год назад +4

    can you please put in a link for a colab notebook for this

  • @ilhemwalker9145
    @ilhemwalker9145 9 месяцев назад +2

    hey please i copied the same line but i'm getting error : autotrain [] llm: error: the following arguments are required: --project-name. i don't know what to do

  • @krishnareddy9
    @krishnareddy9 Год назад +1

    Thank you for the video, I am looking forward video about how to prepare our own dataset without using huggingface dataset !!

    • @engineerprompt
      @engineerprompt  Год назад +1

      It's up now, enjoy!

    • @bookaffeinated
      @bookaffeinated 8 месяцев назад

      @@engineerprompt video link please.... And this one-line command throws error on colab: unknown argument, any suggestions pls?

  • @swauce507
    @swauce507 Год назад +2

    After you finetune the model, how do you use it as a chat interface to query the model and see its results?

  • @SarahAmelia-l8t
    @SarahAmelia-l8t Год назад

    Great video thank you! I have a question; I have a prompt, an output from a model, and a desired output, how I can format this data, please?

  • @alx8439
    @alx8439 Год назад +2

    Does it use lora or qlora techniques?

  • @justabacteria
    @justabacteria Год назад +2

    Could you explain or make a video on how to use your new fine-tuned model?

  • @CrazyFanaticMan
    @CrazyFanaticMan Год назад +2

    At 5:08, what file format does it expect? Sorry, my english is not that good

    • @carlsagan9808
      @carlsagan9808 Год назад

      I'm pretty sure they mean .csv file

    • @NikONEplay
      @NikONEplay 4 дня назад

      Здарова мужик

  • @aiwesee
    @aiwesee Год назад +1

    For fine-tuning of the large language models (llama-2-13b-chat), what should be the format(.text/.json/.csv) and structure (like should be an excel or docs file or prompt and response or instruction and output) of the training dataset? And also how to prepare or organise the tabular dataset for training purpose?

    • @rainchengcode4fun
      @rainchengcode4fun Год назад

      timdettmers/openassistant-guanaco has introduction about the dataset, it should be a list of json with instruction, response in it.

    • @GEfromNJ
      @GEfromNJ Год назад

      See this is one the thing that gets completely glossed over in videos like this. If you take a look at timdettmers/openassistant-guanaco, you'll see that it's some nicely formatted data. It doesn't answer the question about how someone would take their own data and get it into this format.

  • @arjunv7055
    @arjunv7055 Год назад +4

    some of my friends who followed this tutorial mentioned they see an argument issue. I think it is because of the command being broken down into multiple lines. Running the command in multiple lines requires a '\' to be added at the end of every line. Final command should look like this
    !autotrain llm --train --project_name '' \
    --model TinyPixel/Llama-2-7B-bf16-sharded \
    --data_path timdettmers/openassistant-guanaco \
    --text_column text \
    --use_peft \
    --use_int4 \
    --learning_rate 2e-4 \
    --train_batch_size 2 \
    --num_train_epochs 3 \
    --trainer sft \
    --model_max_length 2048 \
    --push_to_hub \
    --repo_id /'t \
    --block_size 2048 > training.log &

    • @nayyershahzad8051
      @nayyershahzad8051 11 месяцев назад

      getting following error, kindly help:
      autotrain [] llm: error: the following arguments are required: --project-name

    • @avataraang3334
      @avataraang3334 4 месяца назад

      @@nayyershahzad8051 same here

  • @learn2know79
    @learn2know79 Год назад +1

    Hi Thanks for the detail explanation. Could you please make another video explaining the RLHF with code implementation.

  • @dec13666
    @dec13666 Год назад +2

    Nice video!
    A recurring aspect I have seen amongst these tutorials however, is that they never mention how to use the custom LLM model (i.e., doing some inference with the custom LLM model), or how to obtain metrics about it... Do you have any other video, where you discuss those 2 topics?
    Thank you!

  • @adriantang5811
    @adriantang5811 Год назад

    Great Sharing again. Many thanks!

  • @Noscov
    @Noscov Год назад

    Thanks for the video. I have a further question. At 5:50 your dataset has the columns instruction and input. What is the input-column for?

  • @oxydol3456
    @oxydol3456 7 месяцев назад

    learnt a lot from the video.Thanks. Is it easy to revert the model to the state before a tuning?

    • @engineerprompt
      @engineerprompt  7 месяцев назад +1

      Thanks, yes, you are merging the extra "LoRA Adapters" layers to the model. The actual model actually remains unchanged so you can just reuse it for other purposes.

  • @Koyaanisqatsi2000
    @Koyaanisqatsi2000 Год назад

    Thank you very much! Where can I view the loss of my training or evaluation data using this method?

  • @caiyu538
    @caiyu538 Год назад

    How to save the fine tuned model to local disk instead of pushing to hub. Could you show us the model pushed to hub? These video graphs will make it clearer. Great.

  • @vijayendrasdm
    @vijayendrasdm Год назад

    What is the relation between max token size and the model kind of repeats itself ? The one you talk in the things to consider

  • @miriamramstudio3982
    @miriamramstudio3982 Год назад

    Thanks for the update. Very interesting.

  • @gamingisnotacrime6711
    @gamingisnotacrime6711 Год назад +1

    I have a custom dataset with 50 rows. For how many epochs should i fine tune thr model?
    Each line in my dataset is in this format - ###Human: Who is John?### Assistant: John is a famous youtuber
    (My dataset has only a single column named text and 50 rows which have the data in above format
    So also are there any issues with my dataset?

  • @emrahe468
    @emrahe468 Год назад +1

    finished running the autotrain in about 6h. And upload the model to hugginface. so what to do next? How to use this?

  • @mdfarhananis8950
    @mdfarhananis8950 Год назад +1

    Please teach how to create dataset for finetuning

  • @noraalzamil2660
    @noraalzamil2660 Год назад

    Thank you very much 🙏
    Can I apply it with TheBlock llama-2-7b ggml?

  • @prestonmccauley5467
    @prestonmccauley5467 Год назад +2

    I followed this exactly in collab, but seems that something is wrong with the arguments, Can you share your colab file?

    • @arjunv7055
      @arjunv7055 Год назад

      if you are breaking the command into multiple line please make sure to add \ towards the end so finally the command looks like this
      !autotrain llm --train --project_name '' \
      --model TinyPixel/Llama-2-7B-bf16-sharded \
      --data_path timdettmers/openassistant-guanaco \
      --text_column text \
      --use_peft \
      --use_int4 \
      --learning_rate 2e-4 \
      --train_batch_size 2 \
      --num_train_epochs 3 \
      --trainer sft \
      --model_max_length 2048 \
      --push_to_hub \
      --repo_id / \
      --block_size 2048 > training.log &

  • @ilyaskydyraliev6498
    @ilyaskydyraliev6498 Год назад

    Thank you for the video! May I ask, how big of a dataset should I have to see that fine tuning actually worked and model learnt new data?

  • @pareak
    @pareak 11 месяцев назад

    What is the difference between the SFT and the Generic trainer?

  • @PajakRikiAkbar
    @PajakRikiAkbar Год назад +1

    I haven't tried it on colab yet but was wondering, do we need colab pro or colab pro+ for this tutorial?

    • @engineerprompt
      @engineerprompt  Год назад +3

      For this, you can use the sharded model with free version but for full model you will need pro

  • @okopyl
    @okopyl Год назад

    Amazing, but how to do the inference properly with this peft thing?

  • @georgekokkinakis7288
    @georgekokkinakis7288 Год назад +1

    I really love your tutorials, they are deeply informative. I was wondering for the following. Unfortunately 😔 all these LLMs are trained in English , but the world has so many other languages. If I follow the fine tuning you described in your video would I be able to fine tune the lama model for a specific dataset which has questions about mathematical definitions and methodologies with their according responses written in Greek? The amound off samples is about 100 questions with answers, I know it is really small but could this give good results for thebspecific dataset? And one last question , do you know any multilingual LLM which supports Greek. Thanks once more and keep up with your excellent ❤ presentations.

    • @AymanEL-BACHA
      @AymanEL-BACHA Год назад +1

      hi @georgekokkinakis7288, have you tried training with your 100 sample/questions ? any improvements ?

    • @georgekokkinakis7288
      @georgekokkinakis7288 Год назад

      @@AymanEL-BACHA No I haven't yet

  • @DikHi-fk1ol
    @DikHi-fk1ol Год назад +1

    Please make another tutorial on how to fine-tune a model on custom dataset rather than using the hugging face ones.

  • @MaralSheikhzadeh
    @MaralSheikhzadeh Год назад +1

    well explained video. thank you:)

  • @Noshiru
    @Noshiru 7 месяцев назад

    Hello!
    The question might be stupid, but how come this is so difficult to learn to the AI our own data ? I mean, when you talk to ChatGPT for example, if you tell it stuff, it will remember (if you use the same chat) what you said and it will be able to answer your questions about it. Why can we just give the AI a documentation for example ?

  • @adapalarajyalakshmi3728
    @adapalarajyalakshmi3728 Год назад +2

    Thanqu for the video can u explain how to use postgress database dataset

    • @Dave-nz5jf
      @Dave-nz5jf Год назад

      you would probably need to pull the data in batches, in the right format, and then run this autotrainer on a batch basis. But it's an interesting question - if you have data that's changed (in the database), and you retrain the model, how does the updated data impact the model output.

  • @sb98052
    @sb98052 Год назад +1

    Thank you for these very clear videos. Do you have any thoughts or pointers on resources for doing this type of training on code models such as CodeLlama?

  • @MicaleAntonio
    @MicaleAntonio Год назад

    Does auto train do multi-label text classification?

  • @anantkabra6825
    @anantkabra6825 Год назад +1

    Hello I am getting this error can someone please help me out with it: ValueError: Batch does not contain any data (`None`). At the end of all iterable data available before expected stop iteration.

  • @ajaym4257
    @ajaym4257 10 месяцев назад +2

    usage: autotrain []
    AutoTrain advanced CLI: error: unrecognized arguments: --use-int4 --learning-rate 2e-4 --num-train-epochs 3 --model-max-length 2048
    i'm getting this error

  • @machineUnlearner
    @machineUnlearner 10 месяцев назад

    i have a time series data, with 7 to 10 parameters. What should I do ?

  • @deepakkrishna837
    @deepakkrishna837 Год назад

    Hi Great Video. Thanks a lot for this. QQ: if I am building an information extractor and the max token length of the training data is 2750 and hence I have kept model_max_length as 3000. Do I need to strictly keep the block_size as well to 3000? Please answer!

  • @白泽-x2n
    @白泽-x2n 11 месяцев назад

    Hello, I am a beginner in LLM. I generated the model folder locally according to the video operation, but the folder size is only about 130Mb. The base model I use is 7b llama2. Is this normal? Why is the model size reduced so much? How do I get the normal size model? I would be grateful if you could answer it for me

  • @sohailhosseini2266
    @sohailhosseini2266 Год назад

    Thanks for sharing!

  • @ajlahade2201
    @ajlahade2201 Год назад

    can you please make a video on how to push this model to hugging face (like production level with model card) and call that model

  • @PickaxeAI
    @PickaxeAI Год назад

    What GPU should we select to complete this training? Could the T4 handle it?

  • @fangxiaoyuan-fm6vr
    @fangxiaoyuan-fm6vr Год назад

    Could you introduce how to deploy our model to a website? Thanks!

  • @nufh
    @nufh Год назад

    Other than google colab, what is other platform that we can use? I'm still new, just started to learn about python.

  • @fpena06
    @fpena06 Год назад +1

    What's a sharded version and why did you go with a sharded version model? Thanks

    • @phoenixfire6559
      @phoenixfire6559 Год назад +6

      Every LLM model works best on a GPU because GPU's excel in parallel calculations. Loading a model into a GPU needs a set amount of VRAM, the amount depends on the parameters of the model and the precision e.g. a 7bn Llama-2 model at 16 float precision will need around 16GB VRAM. I believe the free Colab GPU VRAM is 12GB so you cannot load the 7b model at 16fp precision - you could at 8 bit precision though.
      One way to get around this is to split the model into shards - this is not the same as splitting the model into 3 files. When you download a model from huggingface it is often in multiple pieces, however this is just for ease for download/ help build fault tolerance i.e. protection if one piece is corrupted. When loading these models into the GPU, it is done in series, so for 7b 16fp model, it will still take 16GB VRAM.
      Sharding also splits a model into pieces but it does it in a way that each piece can still talk to the other while still being separate. In a nut shell, you are loading the pieces in parallel. Therefore, as long as you can fit the largest piece, you should be able to load in the whole model. For the one in this video, I believe it is sharded into 5GB VRAM pieces. Note, sharding has some issues:
      1. A sharded and unsharded model may behave slightly differently
      2. Sharded models will take longer to train because data has to go between multiple pieces
      3. Combining the sharded model back to an unsharded model may not yield the same results as a trained unsharded model even if using the exact same data

    • @fpena06
      @fpena06 Год назад

      @@phoenixfire6559 thank you so much for the detailed explanation 👏

  • @tubesarkilar
    @tubesarkilar Год назад

    can you show a sample of time series data file to feed into Autotrain?

  • @bfam7110
    @bfam7110 Год назад

    Is there embeddings or RAG with this approach?

  • @Homboy_
    @Homboy_ Год назад

    Which llama 2 based model can you recommend for text classification problems?

    • @engineerprompt
      @engineerprompt  Год назад +1

      The bigger the better.

    • @Homboy_
      @Homboy_ Год назад

      @@engineerprompt ok thanks, and can't I tokenize my data and give to model for tuning? Also if when u give just 1 column text data as input and Target column is text classification like fraud/normal. What should be the input format in CSV

  • @nexusinfosec
    @nexusinfosec Год назад +1

    Could you please create a video on the dataset creation?

    • @VadiyalaRR
      @VadiyalaRR Год назад

      ruclips.net/video/-ui8YKz4d-E/видео.html hope it helps you

  • @prakhargurha267
    @prakhargurha267 Год назад

    2 questions. Is autotrain-advanced fine tuning is only available as a CLI format, or any other technique i available?Do we need collab pro for llama-2-7b-bf16.Can you suggest some smaller models to try?

  • @okopyl
    @okopyl Год назад

    Now when i generate responses, i get input generated as well. Why? How to avoid that?

  • @youwang9156
    @youwang9156 Год назад

    thank you for ur video, literally save my life, just have one little question about the prompt format, you were using ### human and ### Assistant, so does this format basically depend on the pre-train model prompt format? like Llama-2 chat which has a certain unique format, but some like the Llama 2 base model, if there's no specific mention of that, then we can define our own format for the prompt? do I understand it correctly ? Thank you for your video again !!!!

    • @engineerprompt
      @engineerprompt  Год назад

      Glad you found it helpful. The template depends on whether you are using the base or the chat version. For the base model, you can define your own template as I am doing here because there is no template for it for using it as assistant (base model is actually the next word prediction model). But if you are finetuning a chat version then you will have to use the specific template that was used for finetuning the model. Hope this helps

  • @sravanavvaru4473
    @sravanavvaru4473 Год назад

    hey the thing I did not get is on what data is the model getting trained ??

  • @AA-rd6nm
    @AA-rd6nm Год назад

    Very deatiled thanks for sharing. I ❤ it.

  • @hamedhaidari4479
    @hamedhaidari4479 11 месяцев назад +1

    i followed everything like you, i get this error
    autotrain [] llm: error: the following arguments are required: --project-name

    • @onesecondnanba
      @onesecondnanba 11 месяцев назад +1

      same problem

    • @onesecondnanba
      @onesecondnanba 11 месяцев назад

      autotrain llm \
      --train \
      --project-name 'llama2-openassistant' \
      --model TinyPixel/Llama-2-7B-bf16-sharded \
      --data-path timdettmers/openassistant-guanaco \
      --peft \
      --lr 2e-4 \
      --batch-size 4 \
      --epochs 3 \
      --trainer sft \
      > trainer.log

  • @SadeghShahmohammadi
    @SadeghShahmohammadi Год назад

    It took a few hours, everything went well but at the end the model is not in my hf repository! Cannot find it anywhere!

  • @meteor1
    @meteor1 Год назад

    Can I fine-tune llama-13b-GPTQ using autotrain-advanced ?

  • @ShiftKoncepts
    @ShiftKoncepts Год назад

    I am a little confused, so the Llama LLM on gpt4all has to be trained first before usage with local docs?

  • @AdamTwardoch
    @AdamTwardoch Год назад +4

    But what's "a while"? Hours? Days?

    • @adbeelomiunu
      @adbeelomiunu Год назад

      😂
      Funny but a great question to ask

    • @phoenixfire6559
      @phoenixfire6559 Год назад +5

      In the video @11:29 it looks like he's been running the training for 44 minutes and it still has over 43 hours to run. The Guanaco data set he used has 10k instructions and let's assume 250 tokens per instruction, that's 2.5 million token dataset. The Alpacae dataset he mentions is 52k instruction and around 10 million tokens.
      Remember he's using a batch size of 2, if he ran with a batch size of 8 (assuming he had enough vram), then it would take 1/4 the time.

    • @fuba44
      @fuba44 Год назад +2

      If it helps, i ran hes exact example on an nvidia tesla P40 with 24gb of vram (changed the batch size from 2 to 5) and it toke me 20 hours.

    • @emrahe468
      @emrahe468 Год назад +1

      finetuning 6.6K sized database took me like 6h on google colab pro. but on some other tutorials, this was like 30 min. im totally lost

  • @abdullahbinmubarak1
    @abdullahbinmubarak1 5 месяцев назад

    Thanks Brother 😍

  • @pickaxe-support
    @pickaxe-support Год назад

    Is there a link for the google colab notebook?

  • @titangadget
    @titangadget 9 месяцев назад

    I'm using this one line training code but is giving me error... can you update it?

  • @sanj3189
    @sanj3189 Год назад

    How can i use LLama2 for generating synthetic data

  • @souvickdas5564
    @souvickdas5564 Год назад

    Can we fine-tune LLaMA model on MNLI or SNLI dataset? Is it worth doing ? Give me your thought.

    • @engineerprompt
      @engineerprompt  Год назад

      Yes, I think it’s possible. These might already be in the training data.

  • @bahramboutorabi5971
    @bahramboutorabi5971 Год назад

    Great video. Thank you

  • @BatoolZ-q5r
    @BatoolZ-q5r 5 месяцев назад

    do we have to add the tiny pixel model to colab?

  • @nitingoswami1959
    @nitingoswami1959 Год назад

    Can we train this model on any data or it requires some specific format ? Does every llm requires some specific tabular data or any raw data ?

  • @陸賢豐
    @陸賢豐 Год назад

    Is it requried a dataset format for fine-tuning model, or is just a suggestion in the video? thz

    • @engineerprompt
      @engineerprompt  Год назад +1

      For auto train you need to have a text column in your csv. The format can be anything you want

    • @陸賢豐
      @陸賢豐 Год назад

      thz bro !@@engineerprompt

  • @user-wr4yl7tx3w
    @user-wr4yl7tx3w Год назад

    Why is there such sharded versions of the model?

  • @bharatkaushik9916
    @bharatkaushik9916 Год назад

    Can someone tell how to inference this model ?after pushing it to hub thanks

  • @AtharvaWeginwar
    @AtharvaWeginwar 10 месяцев назад

    I am facing issues in the autrain line where its stating argument should be project-name instead of project_name and even if i change that its not taking arguments like data_path, use_peft. can someone help me out?

  • @okopyl
    @okopyl Год назад

    Why do you use that kind of prompt for the training like `### Instruction` or `### Human`? When in fact Llama 2 prompts are like `[INST] `...

    • @engineerprompt
      @engineerprompt  Год назад

      The prompt template you have mentioned is for the chat version. I am fine tuning the base version of the model. Here you have the flexibility to define your own template the way you like

  • @jesusic1320
    @jesusic1320 Год назад +1

    A doubt I cannot solve anywhere: running this locally is free right? And after that, can you use it to generate images locally, also for free? I'd like to practice but avoid costs of that practice. I think for example Replicate runs the training online, so you have to pay.
    But I have a GTX3070 so I think I can do my practice locally for free

  • @tensiondriven
    @tensiondriven Год назад +1

    Can you train against GPTQ's using this?

    • @engineerprompt
      @engineerprompt  Год назад

      Yeah, I think you will be able to. However, remember this is not the chat version, it's the base model.

  • @akibulhaque8621
    @akibulhaque8621 Год назад

    If the dataset is made using my native language when will the model still be trained for that specific language?

    • @engineerprompt
      @engineerprompt  Год назад

      You will need to make sure the tokenizer also supports the language otherwise you will run into issues

  • @MohamedElGhazi-ek6vp
    @MohamedElGhazi-ek6vp Год назад

    interesting work thank you , what if I have data on pdf format and i want fine tune my data on question answering model

    • @engineerprompt
      @engineerprompt  Год назад

      You will need to convert that into text. Will be making a video on how to create a dataset.

    • @MohamedElGhazi-ek6vp
      @MohamedElGhazi-ek6vp Год назад

      @@engineerprompt thank
      you againe