I used LLaMA 2 70B to rebuild GPT Banker...and its AMAZING (LLM RAG)

แชร์
ฝัง
  • เผยแพร่เมื่อ 25 ธ.ค. 2024

ความคิดเห็น • 206

  • @moondevonyt
    @moondevonyt ปีที่แล้ว +44

    first off, respect for the hustle and the in-depth breakdown of integrating llama with other tools
    really shows how much work goes behind the scenes
    that said, not sure why everyone's so hyped about all these new models when sometimes simpler and older architectures can do the trick
    but hey, if it's all about pushing boundaries and experimenting, you're killing it bro!

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว +6

      Thanks a mill moondev!! Yah at this point I'm just pushing to see where it's going, I started fine tuning this for some custom use cases and it looks hyper promising though!

    • @xt3708
      @xt3708 ปีที่แล้ว +2

      Thanks so much for the detailed videos @@NicholasRenotte Can you make a video on fine tuning?

    • @vyrsh0
      @vyrsh0 ปีที่แล้ว +3

      can you name some of the old models? so I can look them up and learn about them?

    • @ZombiemanOhhellnaw
      @ZombiemanOhhellnaw ปีที่แล้ว

      @@vyrsh0 @moondevonyt yes, I would like to learn what older models do the trick as well!

  • @yudhiesh1997
    @yudhiesh1997 ปีที่แล้ว +120

    You can’t load Llama2-70b on a single A100 GPU. Using full precision(float-32) would require 70billion * 4 bytes = 280GB of GPU memory. If you load it using float-16 it would reduce by half to 140GB. It finally worked cause you loaded it in int-8 which only requires 70GB of memory while the A100 has 80GB of GPU memory. If you wanted to load it in full/half precision you would need multiple GPUs and also need to leverage tensor parallelism whereby you slice the tensors across multiple GPUs.

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว +12

      I'm not sure that was it, I successfully loaded in half precision over 2xA100-80GB (didn't show the loading in the vid). But when I went to generate this is what I came up against: github.com/huggingface/transformers/issues/24056. Solid calcs though!

    • @sluggy6074
      @sluggy6074 ปีที่แล้ว +9

      That's nice. I'll just have to settle for my quantized 70b LLMs that run hot and fast on my 4090.
      I think I can live with this.

    • @agusavior_channel
      @agusavior_channel ปีที่แล้ว +1

      Use petals

    • @seanhuver4813
      @seanhuver4813 ปีที่แล้ว

      It runs nice @ 4bit precision on A6000.

    • @bubbleboy821
      @bubbleboy821 ปีที่แล้ว

      What you meant to say was that you can load LLama2-70b on a single A100 GPU, you just have to run it in int-8.

  • @Principality92
    @Principality92 ปีที่แล้ว +9

    Always looking forward to your videos...
    I've an MSc. In AI, but I still learn from you 👏🏼

    • @MikeAirforce111
      @MikeAirforce111 ปีที่แล้ว +12

      I have a PhD and I am here as well 🤷‍♂

    • @siestoelemento4027
      @siestoelemento4027 ปีที่แล้ว

      I guess I'm on the right path then
      @@MikeAirforce111

  • @splitpierre
    @splitpierre 10 หลายเดือนก่อน +2

    Yeah, nice work!
    I've been playing around RAG as well, I can relate to all roadblocks and pain points.
    I'm trying to squeeze as much as possible so I can have a decent RAG, without any fancy GPU, consumer grade hardware running everything local, it's been fun/painful

  • @MikeAirforce111
    @MikeAirforce111 ปีที่แล้ว +5

    This video was great. You have created a format that is very entertaining to watch! 🙌 Subbed!

  • @malice112
    @malice112 ปีที่แล้ว +7

    NIcholas I love your videos and your way of making learning about ML/AI fun! In your next video can you please show us how to fine-tune a LLM model! Thanks for all the hard work you do on making these videos!

  • @FunCodingwithRahul
    @FunCodingwithRahul ปีที่แล้ว +3

    Incredible stuff done... thank you Nich.

  • @shipo234
    @shipo234 ปีที่แล้ว +3

    Nick this is insanely good, thank you for the effort

  • @dacoda85
    @dacoda85 ปีที่แล้ว +3

    Love this style of video. Fantastic content as always mate. You've given me some ideas to try out. Thanks :)

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว +1

      🙏🏽 thanks for checking it out!

  • @projecttitanium-slowishdriver
    @projecttitanium-slowishdriver ปีที่แล้ว +1

    Huge thanks for you videos. Nowadays I code, demonstrate, and perhaps lead AI, ML, DL, and RL development in 1300 + worker engineering and consulting company
    I am combining technical analysis tools (fem, CFD, MBS…) with AI to generate new digital business cases

  • @sinasec
    @sinasec ปีที่แล้ว

    well done. one of the best and compact tutorial I ever had. Thanks for providing the source code

  • @andreyseas
    @andreyseas ปีที่แล้ว +1

    Sick production value and great content!

  • @ShaneZarechian
    @ShaneZarechian 11 หลายเดือนก่อน

    Taking the viewers along the development and debugging ride is a cool style

  • @kevynkrancenblum5350
    @kevynkrancenblum5350 ปีที่แล้ว +1

    2:40 😂
    Thanks Nic the video is awesome ! 🤘🏽🤘🏽🤘🏽

  • @hongyiyilim6830
    @hongyiyilim6830 ปีที่แล้ว

    Great content! helped me alot with building my own open source model RAG

  • @Nick_With_A_Stick
    @Nick_With_A_Stick ปีที่แล้ว +2

    My computer is currently training a lora on stable 7b for natural language to (30k)python, and (30k)sql. I also Included (30k)orca questions so it dosent loose its abilities as a language model, and 20k sentiment analysis for new headlines. I would love to try this model with this as soon as Its done training.

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว

      Noiceee, what data sets you using for Python?

  • @achuunnikrishnan-w1h
    @achuunnikrishnan-w1h 9 หลายเดือนก่อน

    I love you nicholas....you are awesome .my only regret is that i didn't found you earlier. all my dream projects in a channel....thankyou

  • @ShahJahan_NNN
    @ShahJahan_NNN ปีที่แล้ว +2

    please make a video on ocr on past question papers that can extract questions, and extract keywords and analyse with 10 years papers, and predicts upcoming questions

  • @juanpablopereira1479
    @juanpablopereira1479 ปีที่แล้ว +6

    I think "Amazing" falls short, the amount of knowledge, the fact that your using cutting edge Open source model and all of that in a really funny and light tone. Keep up the good work! I have a question, do you think is much harder to deploy that app into google cloud run compared with runpod?

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว

      Thanks so much Juan! I can't imagine it would be running on a VM instance with GPUs attached. Could also separate out the LLM bit and run that solely on a GPU then just run the app on a basic linux instance!

  • @richardbeare11
    @richardbeare11 ปีที่แล้ว

    Love your videos Nicholas. Watching this with my morning coffee, a few chuckles, and a bunch of "ooohhh riiiiiight!"s. Your vid bridged a bunch of gaps in my knowledge.
    Gonna be implementing my own RAG now 😎👍

  • @autonomousreviews2521
    @autonomousreviews2521 ปีที่แล้ว +1

    Great share! Thank you for your persistence and giving away your efforts :)

  • @daniamaya
    @daniamaya ปีที่แล้ว

    wow! This is top-tier content. Thank you!

  • @wayallen831
    @wayallen831 ปีที่แล้ว +2

    Great tutorial! Can you also help do a tutorial on setting up runpod to host the application on it? Found that part to be a bit confusing and would love a more thorough walk thru. Thanks for all you do!

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว

      Ya, might do something soon and add it to the free course on Courses From Nick. I'm saving infra style/setup videos for the Tech Fundamentals course.

  • @PritishMishra
    @PritishMishra ปีที่แล้ว +1

    Amazing editing and content, learnt a lot.

  • @nimeshkumar8508
    @nimeshkumar8508 ปีที่แล้ว +1

    Thankyou so much for this. God bless you

  • @kallamamran
    @kallamamran ปีที่แล้ว

    I so wish I could do this. Maybe not specifically THIS, but things like this. I wish I understood the underlying principles for making something like this work, Great video!!!

    • @kallamamran
      @kallamamran ปีที่แล้ว

      @@jimmc448 Ha ha ha...

  • @Bliss_99988
    @Bliss_99988 ปีที่แล้ว +1

    'How to start a farm with no experience' - Hahaha, man, I just want to say that I love your sense of humour. Also, your videos are really useful for me, I'm an English teacher and I'm trying to build useful tools for my students. Thanks for your content.

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว

      😂 it's my secret dream job! Hahah thanks so much for checking it out man!!

  • @angelazhang9082
    @angelazhang9082 8 หลายเดือนก่อน

    Hi Nick... really late but would be super grateful for a response. I'm trying to figure out how you used RunPOD for this. It looks like you created a folder to store the weights instead of using one of their custom LLM options. Did you pay for extra storage? I can't imaging you loaded all the weights each time you needed to use this on the cloud. I'm new to working with these models and cloud GPUs, so any help is greatly appreciated!

  • @horane
    @horane ปีที่แล้ว

    minute 4:45 comment is confirmation clutch! Never give up!

  • @deadcrypt
    @deadcrypt ปีที่แล้ว +1

    8:57 nice auth key you got there

  • @hebjies
    @hebjies ปีที่แล้ว +4

    It is possible that when you tried to load the pdf with SimpleDirectoryReader, it was skipping pages, because of the chunk size /embedding model you selected, the model you selected (all-MiniLM-L6-v2) is limited to 384 while the chunk you specified was 1024, maybe and just maybe, that is why I think it was skipping pages, because it was unable to load all the chunk in the embedding model

  • @synthclub
    @synthclub 10 หลายเดือนก่อน

    Really cool llama application. Really Impressive.

  • @knutjagersberg381
    @knutjagersberg381 ปีที่แล้ว +1

    Do you really have to get access by Meta to use the weights? My current interpretation is that you enter the license agreement as soon as you use the weights, where ever you got them (as you're also allowed to redistribute them).
    I'm not 100% sure about this, but I think you don't need to register. I think that's more for them to keep track of early adopters.

  • @micbab-vg2mu
    @micbab-vg2mu ปีที่แล้ว +1

    Great video - thank you

  • @tejaskumarreddyj3133
    @tejaskumarreddyj3133 5 หลายเดือนก่อน

    Can you please make a video explaining what is the LLM to use when developing a RAG!! It would be of great help if you could make one and also please tell us about how to run this locally on linux!!😁

  • @20S030SHIVAYAVASHILAXMIPRIYA.S
    @20S030SHIVAYAVASHILAXMIPRIYA.S ปีที่แล้ว +1

    What are the difference between the meta released llama 2 models , hf models and quantised model (ggml) files found in the hugging face? Why cant we use the meta/llama-2-70b model ?

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว +1

      You could! llama-2-70b is the base model, chat is the model fine-tuned for chat. the GGML model is a quantized model (optimized for running on less powerful machines). The hf suffix indicates that it's been updated to run with the transformers library.

    • @poornipoornisha5616
      @poornipoornisha5616 ปีที่แล้ว

      @@NicholasRenotte The 70b chat model downloaded from meta has consolidated.pth files in it. How to use the files to finetune the model for custom datasets ?

  • @DGFilmsNYC
    @DGFilmsNYC ปีที่แล้ว +1

    Thank you brother

  • @i2c_jason
    @i2c_jason ปีที่แล้ว +1

    ...Sunday morning after a bender hahhaaha bro I love you.

  • @ricowallaby
    @ricowallaby ปีที่แล้ว

    Hi, just found your channel and enjoying it, but I can't wait till we have real Open Source LLMs, anyway keep up the good work, cheers from Sydney.

  • @Tripp111
    @Tripp111 ปีที่แล้ว

    Thank you. ❤️🍕

  • @Ryan-yj4sd
    @Ryan-yj4sd ปีที่แล้ว +1

    Nice video. You seem to have the taken the tough route. I didn't have as much trouble :)

  • @mfundomonchwe1313
    @mfundomonchwe1313 ปีที่แล้ว +1

    This is awesome!

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว +1

      Thanks a mil!!

    • @mfundomonchwe1313
      @mfundomonchwe1313 ปีที่แล้ว +1

      please attempt the DAG context {model} next, would love to see that, sort of like Causal inference model@@NicholasRenotte

  • @en-iyi-benim
    @en-iyi-benim ปีที่แล้ว +1

    You make me love machine learning more

  • @yashsrivastava4878
    @yashsrivastava4878 ปีที่แล้ว

    hey can it be done on chainlit along with LMQL and Langflow added to it, output shows pdfs file as a reference and scores based on whether its retrieves factual data or makes up its own answer

  • @fur1ousBlob
    @fur1ousBlob ปีที่แล้ว +1

    I wanted to use llama in a chatbot. Do you know if that will be possible? I want to know your opinion. I am using rasa framework to build the chatbot but I am not sure how to integrate it.

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว

      Sure can! Seen this? forum.rasa.com/t/how-to-import-huggingface-models-to-rasa/50238

  • @mohamedkeddache4202
    @mohamedkeddache4202 ปีที่แล้ว

    please help me 😓
    ( in your videos of licence plate tensorflow)
    i have this error when i copy the train command in cmd :
    ValueError: mutable default for field sgd is not allowed: use default_factory

  • @warthog123
    @warthog123 7 หลายเดือนก่อน

    Excellent video

  • @nfic5856
    @nfic5856 ปีที่แล้ว +2

    How can it be scalable, since this deployment costs like 2$ per hour? Thanks.

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว +1

      Didn't show it here but if I were scaling this out, the whole thing wouldn't be running on a GPU. The app would be on a lightweight machine and the LLM running on serverless GPU endpoints.

    • @Ryan-yj4sd
      @Ryan-yj4sd ปีที่แล้ว +1

      @@NicholasRenotte but you would still need to pay to rent an A100 GPU which around $1 to $4 per hour

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว

      Yeah, no real way around that, gotta host somewhere! Especially so if you want to be able to use your own fine-tuned model eventually (coming up soon)!

    • @nfic5856
      @nfic5856 ปีที่แล้ว

      Does gpt3.5-turbo (4k or 16k context) remain cheaper in a small production scale?

  • @himanshuahujaofficial7813
    @himanshuahujaofficial7813 9 หลายเดือนก่อน

    Nick, thank you so much for the great content. I’m new to AI and want to build an LLM for my startup, but I’m not sure where to start. Can you recommend something?

  • @scottcurry3767
    @scottcurry3767 ปีที่แล้ว +1

    RunPod A100 instances are looking scarce, any tips on how to adapt for multiple GPU instances?

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว

      Going to give it a crack this week, i've got a fine tuning project coming up. Will let you know. The other option is to use the GGML/4 bit quantized models, reduces the need for such a beefy instance. Also, check out RunPod Secure Cloud, a little pricier but seems to have more availability (I ended up using SC when I was recording results for this vid because the community instances were all unavailable). Not sponsored just in case I'm giving off salesy vibes.

  • @ba70816
    @ba70816 ปีที่แล้ว +1

    Really great content, you might have the most effective style I’ve ever seen. Well done. I can’t remember which video I saw where you spoke about your hardware setup. It’s cloud based isn’t it?

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว

      Thanks a mil! This particular instance is cloud based, yup! It's all runpod, I used a remote SSH client to use the env with VsCode. Old HW vid might have been this: th-cam.com/video/GH1RuKguO54/w-d-xo.html

    • @ba70816
      @ba70816 ปีที่แล้ว

      Would you consider a video showing the setup process you use?

  • @zamirkhurshid261
    @zamirkhurshid261 ปีที่แล้ว +1

    Nice sharing sir your way of teching is very helpful for biggner. Please make a video how we can make deep learning model on earthquake dataset as you have make a project on image classification.

  • @randomthoughts7838
    @randomthoughts7838 ปีที่แล้ว

    Hey, is there some structured way(steps) to learn to work with llms. As an analogy, DSA is one structured way to solve coding problems. I am new to llms realm and any advice is much appreciated.

  • @emanuelsanchez5245
    @emanuelsanchez5245 ปีที่แล้ว

    Hi!
    What was the performancee of the method?
    How many tokens per second with that deployment?

  • @chrisweeks8789
    @chrisweeks8789 ปีที่แล้ว +3

    All facets of your work are incredible! Are the context limits of llama2 similar to that of OpenAI?

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว

      Thanks a mil! Would depend on which models you're comparing!

  • @lashlarue59
    @lashlarue59 ปีที่แล้ว

    Nick you said that you were able to build your lip reading model in 96 epochs. How long in an epoch in real time?

  • @BudgetMow
    @BudgetMow ปีที่แล้ว

    thank you for this tutorial , although i am facing a slight issue in parsing tables from pdfs , i managed to allow the parser to take in multiple documents , and it is answering in a quick time , only issue with if the question is related to data within a table or some times data spanning multiple lines it fails to retrieve that data

  • @fra4897
    @fra4897 ปีที่แล้ว

    TL;DR basic RAG with Llama 70B, nothing more, nothing less - (thanks a lot for the video, really well done)

  • @ytsks
    @ytsks 10 หลายเดือนก่อน

    When someone tells you they made something "as good as" or "better" than chatgpt, remember that even FB do not compare l70b to current gpt-4 turbo, but the previous release.

  • @billlynch3400
    @billlynch3400 4 หลายเดือนก่อน

    where can we find the code that you use in the video? Can you please share it.

  • @jennilthiyam1261
    @jennilthiyam1261 ปีที่แล้ว

    How can we set up llama=-2 on the local system with memory. Not just one time question but interactive conversation like online chatGPT

  • @wasgeht2409
    @wasgeht2409 ปีที่แล้ว +2

    Nice Video! I think it is impossible to use LLaMA 2 70B on a MacPro M1 with 8 GB RAM :( or is there a any chance without cloud services to use it locally ?

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว +1

      Could give it a crack with the GGML models, haven't tried it yet though tbh!!

  • @mrrfrooty
    @mrrfrooty 6 หลายเดือนก่อน

    Hi, could you provide the runpod source code for this? Can't find any outside documentation on how you made this possible

  • @krishnakompalli2606
    @krishnakompalli2606 ปีที่แล้ว

    As you have used RAG method, I'd like to know how it can answer extrapolated questions?

  • @ciberola285
    @ciberola285 ปีที่แล้ว

    Hi Nicolas, are you planing to make a video on training OWL-ViT model?

  • @accelerated_photon2265
    @accelerated_photon2265 ปีที่แล้ว

    Love your videos , would love to deploy a model but the 70B compute is way too much do you have any idea or do you know any website where I can check compute requirements for the 7B model ? Just got my meta access last week thanks again for the video

  • @ml-techn
    @ml-techn ปีที่แล้ว

    Hi, thanks for the video. which gpu are using? I want to buy and build a dl machine to play with llm.

  • @farseen1573
    @farseen1573 8 หลายเดือนก่อน

    What platform you are using for 1.69$/hr gpu? Cant find any good gpu cloud providers🥺

  • @vanshpundirv_p_r9796
    @vanshpundirv_p_r9796 ปีที่แล้ว

    Hey, Can you tell me minimum vram, ram and space required to load and inference from the model?

  • @youssefghaouipearls
    @youssefghaouipearls 5 หลายเดือนก่อน

    Hello, This seems like a less expensive approach than using Google Cloud. How much did it cost?

  • @pantherg4236
    @pantherg4236 ปีที่แล้ว

    What is the best way to learn deep learning fundamentals via implementation (let's say pick a trivial problem of build a recommendation system for movies) using pytorch in Aug 26, 2023? Thanks in advance

  • @CentoDieci-d3p
    @CentoDieci-d3p ปีที่แล้ว

    I am saying Do I need to know metric level math to get Ahead in machine learning or just Know how things work like the specific or library I'm using Pls answer my Question

  • @strangnet
    @strangnet ปีที่แล้ว

    Really interesting, but what was your total cost in the end?

  • @eddysaoudi253
    @eddysaoudi253 ปีที่แล้ว +1

    Hi! Nice video! Is it possible to use llama2 to build an app like autogpt or gpt researcher in a local environment?

    • @Dave-nz5jf
      @Dave-nz5jf ปีที่แล้ว +2

      Essentially runpod is a local environment. It's a linux server in the cloud , but it's no different than local linux server.

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว +1

      Yup, what he said ^!

  • @leonardoariewibowo7867
    @leonardoariewibowo7867 ปีที่แล้ว

    do you use linux? because i cant run this with my windows machine, bitandbytes didn't support windows for cuda >= 11.0

  • @tenlancer
    @tenlancer ปีที่แล้ว

    what is the response time for each query? and which GPU did you use for this app?

  • @jyothishkumar.j3619
    @jyothishkumar.j3619 ปีที่แล้ว

    What are the limation on monetizing Ilama Banker app ? Could please explain?

  • @FrankHouston-v5e
    @FrankHouston-v5e 11 หลายเดือนก่อน

    You are marvelous! I bow down after witnessing your next level hacking skills 🧐.

  • @eel789
    @eel789 ปีที่แล้ว +1

    How do I use this with a react frontend?

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว +2

      Could wrap the inference side of the app up into an api with FastAPI then just call out to it using axios!

  • @Roy-h2q
    @Roy-h2q ปีที่แล้ว

    Gosh when i use GPT4 , it give me a response saying it can not further summarize personal report and it just stop there.
    I think i will just need to switch to a diff models

  • @MrDataStorm007
    @MrDataStorm007 ปีที่แล้ว

    your are a god thank you !

  • @zakaria20062
    @zakaria20062 ปีที่แล้ว

    Waiting open source like function call ChatGpT will be amazing

  • @nevereverlook
    @nevereverlook ปีที่แล้ว +1

    What is your laptop model?

  • @Xhishir_Rahman
    @Xhishir_Rahman 10 หลายเดือนก่อน

    I have learned enter intermediate level machine learning, now can I start deep learning along with machine learning. please sir tell me

  • @singledoutpictures6742
    @singledoutpictures6742 ปีที่แล้ว

    You are a weapon!!!

  • @moshekaufman7103
    @moshekaufman7103 9 หลายเดือนก่อน

    Hey Nicholas,
    It's a little disappointing that you haven't actually released the final model yet, even though you mentioned it in the video. While showing the source code is a good start, it's not the same as actually providing the finished product.
    Unfortunately, without the final model itself, it's difficult to take your word for it. To build trust and transparency, it would be much better to provide a download link for the model so people can try it out for themselves. This would be a much more impactful way to share your work and allow others to engage with it.
    I hope you'll reconsider and release the final model soon!

  • @RamatoulayeDiallo-x5u
    @RamatoulayeDiallo-x5u ปีที่แล้ว

    Hello nicholas,i still not understand the ./model.

  • @sunkarashreeshreya451
    @sunkarashreeshreya451 ปีที่แล้ว

    You are brilliant. I've been trying to find a tutorial for slidebot.. could you work on it ?

  • @evanfreethy8375
    @evanfreethy8375 ปีที่แล้ว

    Wheres the code for the front end website?

  • @vitalis
    @vitalis ปีที่แล้ว +1

    can you do a video about analysing trends from websites such as WGSN?

  • @nimaheydarzadeh343
    @nimaheydarzadeh343 ปีที่แล้ว +1

    it's great , I try to find like this

  • @thepirate_kinz1509
    @thepirate_kinz1509 ปีที่แล้ว

    Can we have a tutorial on conditional GANs please. And multi feature conditional gans as well 😊

  • @vikassalaria24
    @vikassalaria24 ปีที่แล้ว

    i am getting error:ValidationError: 1 validation error for HuggingFaceLLM query_wrapper_prompt str type expected (type=type_error.str). I am using 7b chat llama2 model

    • @divyanshumishra6739
      @divyanshumishra6739 ปีที่แล้ว

      Did you resolved that error? I am gettting same error and iam unable to solve it

  • @willblumrosen4981
    @willblumrosen4981 ปีที่แล้ว

    this man never ceases to disappoint, thank you for all that you do!

  • @malice112
    @malice112 ปีที่แล้ว +1

    I am confused is Llama 2 an LLM or did you use the Huggingface LLM ?

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว +1

      LLaMA 2 70b is the LLM, we loaded it here using the Hugging Face library.

  • @en-iyi-benim
    @en-iyi-benim ปีที่แล้ว +1

    A deep learning in Pytorch video pleaseee

  • @ahmadshabaz2724
    @ahmadshabaz2724 ปีที่แล้ว +1

    How i get free gpu in web server. I don't have gpu.

  • @sergeyfedatsenka7201
    @sergeyfedatsenka7201 ปีที่แล้ว

    Does anyone know if renting GPU is cheaper than using Open AI API? By how much? Thank Nicholas for your great content!

  • @dkhundley
    @dkhundley ปีที่แล้ว +1

    Well done! Have you considered a video around a formal fine tuning of one of the lesser variants (e.g. 7B) version of Llama 2? I’d love to see you do one. 😁

    • @NicholasRenotte
      @NicholasRenotte  ปีที่แล้ว +4

      On the cards for this week DK, had a client ask for it. Actually got a super interesting use case in mind!

    • @dkhundley
      @dkhundley ปีที่แล้ว

      @@NicholasRenotte Awesome! Looking forward to it.

  • @user-pp4ts5ob1u
    @user-pp4ts5ob1u ปีที่แล้ว +1

    Excelet video, you are amazing, please update the video "AI Face Body and Hand Pose Detection with Python and Mediapipe", I can't solve the errors, it would be very useful for my university projects, thank you very much.