The FASTEST way to build CHAT UI for LLAMA-v2

In this video, ill show you the fastest way of building a chatbot user interface (chat ui)! We will be using gradio.
Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)
My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingml
Follow me on:
Twitter: / abhi1thakur
LinkedIn: / abhi1thakur
Kaggle: kaggle.com/abhishek

Пікірлер: 50

  • @abhishekkrthakur
    @abhishekkrthakur Жыл бұрын

    Code is available here: gist.github.com/abhishekkrthakur/a3d712c2709dcfbfa6a803fcfbcb5737 Please subscribe to help me keep motivated to make awesome videos like this one. :)

  • @iamfreelancer1961
    @iamfreelancer1961 Жыл бұрын

    Thank you so much for coming back to your KZread channel. Now we can learn a lot🎉

  • @tusharbedse9523
    @tusharbedse9523 Жыл бұрын

    I am working in data science since last year. I am regularly following ur videos. I feel that u have GREAT content but the level that you teach you is much higher than the aveage ppl(according to me, could b wrong) so if u could plz teach us in a beginner way then it would be very much helpful thank you again!!!! love from india bhai!

  • @PunitPandey
    @PunitPandey Жыл бұрын

    Keep good work Abhishek 👍👍👍 Great videos on LLMs.

  • @dreamypujara3384
    @dreamypujara338411 ай бұрын

    the code seems to work but as i open the gradio url to test it, its showing error as soon as i put in some question

  • @amon0524
    @amon0524 Жыл бұрын

    Thanks! Great work! Could you tell me about set-up on VScode? Docker?

  • @nirsarkar
    @nirsarkar10 ай бұрын

    Amazing content. Thanks

  • @roberthendrickson724
    @roberthendrickson72411 ай бұрын

    Never-minding for a sec that I really appreciate the content of this video, I would love to know how you're doing your recording... especially how are you getting your talking head cutout to superimpose on the video.

  • @ankushaneja9588
    @ankushaneja9588 Жыл бұрын

    i am using python and having llama-2-7b-chat on my linux machine. how can i load the model in above UI. waiting for a response.

  • @anandteerthrparvatikar5359
    @anandteerthrparvatikar53598 ай бұрын

    Hi Abhi, could you pls drop a link of video where we can deploy model by ourselves? Downloaded Llama 2 model to Any Cloud end point?

  • @edan5735
    @edan5735 Жыл бұрын

    Hi Abishek, Thank you for the great content. I just tried your code but I got the same error while prompting . tell me pls Thanks

  • @pavanpraneeth4659
    @pavanpraneeth4659 Жыл бұрын

    Is there a chance to make a video to query a pdf or chat with data will llama2

  • @skullywag5937
    @skullywag593710 ай бұрын

    Can we build a user interface to let llama2 analyze data in excel spreadsheets?

  • @anish9411
    @anish9411 Жыл бұрын

    Hi Abhishek, great video! Quick question, are there any CPU requirements to run this locally?

  • @abhishekkrthakur

    @abhishekkrthakur

    Жыл бұрын

    not really. but note that the endpoint will require GPU and for that, you can take a look at this tutorial: kzread.info/dash/bejne/oWV2pdNqe627fLA.html

  • @Klogomega
    @Klogomega Жыл бұрын

    Great video, Abhishek. Is it possible to host ChatUI on Azure Webapp service? Have you come a cross something like that? Thanks! 🙏

  • @ignacio3714
    @ignacio371411 ай бұрын

    hey friend. it seems that you know a lot!! could you give me a hand with this? I want to know what's the best way of creating your own "chatgpt" but giving a specific amount of X files. Let's say a small book, and then be able to ask questions about it, but running it locally or in the cloud (not using any third party basically). what's the best way of doing it? is it even possible? like running something like that in google colab with files from google drive or something like that? thanks in advance man!

  • @MasterBrain182
    @MasterBrain182 Жыл бұрын

    👍👍👍

  • @anandteerthrparvatikar5359
    @anandteerthrparvatikar5359 Жыл бұрын

    This is great to build a quick poc in 2 hours for presentation

  • @abhishekkrthakur

    @abhishekkrthakur

    Жыл бұрын

    takes 20mins or less. hehe

  • @anandteerthrparvatikar5359

    @anandteerthrparvatikar5359

    Жыл бұрын

    Absolutely, even ppt content from llama... However, Company specific template :)

  • @amitmahajan8989
    @amitmahajan8989 Жыл бұрын

    Can we build a private chatbot using llama 2? The way you developed in your last video using Falcon 40B?

  • @abhishekkrthakur

    @abhishekkrthakur

    Жыл бұрын

    all you need to do is replace the model and use the instructions shown in this video :)

  • @songsong2334
    @songsong2334 Жыл бұрын

    Great Content! One question what's LLAMA_70B linked to? I have a llama-2-7b folder downloaded into my local dev. How can I link that into the os.environ()? Thanks

  • @abhishekkrthakur

    @abhishekkrthakur

    Жыл бұрын

    thanks! described here: kzread.info/dash/bejne/oWV2pdNqe627fLA.html

  • @user-qx7jx1qr4g

    @user-qx7jx1qr4g

    Жыл бұрын

    @@abhishekkrthakur how exactly does this work? It would be super helpful to know. Great work overall!

  • @koshalsingh9786
    @koshalsingh9786 Жыл бұрын

    I am sorry to ask, But I didnt understand what you did at 15:35 to resolve that error? you said that you are exporting the environment variables but why and where?

  • @abhishekkrthakur

    @abhishekkrthakur

    Жыл бұрын

    in the terminal i wrote: export LLAMA_70B=........ where ........ is the path to your endpoint. in case you want to learn how to create this endpoint, check out the other videos in my LLM playlist: kzread.info/head/PL98nY_tJQXZlXLELjCMA8cciKLRE2eLME

  • @koshalsingh9786

    @koshalsingh9786

    Жыл бұрын

    @@abhishekkrthakur thanks for such quick reply

  • @sj0998
    @sj0998 Жыл бұрын

    Can your code handle multiple requests concurrently ? (multiple users asking a question at the same time), is this flask app ?

  • @abhishekkrthakur

    @abhishekkrthakur

    Жыл бұрын

    yes. and no, its not a flask app

  • @sj0998

    @sj0998

    Жыл бұрын

    @@abhishekkrthakurthanks 😊

  • @jdoejdoe6161
    @jdoejdoe616111 ай бұрын

    Thank you for this tutorial. Please, is a video turial on how to sharred a model. I want to sharred this model togethercomputer/Llama-2-7B-32K-Instruct

  • @Kitana808
    @Kitana8082 ай бұрын

    Are you planning on making a chatbot for Llama 3?

  • @foreignconta
    @foreignconta Жыл бұрын

    I laughed at that one line statement of gradio to create a chat interface. Need to try this. Does this format LaTeX? Also, how is 70B running so fast on your machine?

  • @abhishekkrthakur

    @abhishekkrthakur

    Жыл бұрын

    its not running on my machine 🙂 im not surr about latex, unfortunately. worth a try

  • @foreignconta

    @foreignconta

    Жыл бұрын

    @@abhishekkrthakur I see. Will try!

  • @aekanshgupta6642

    @aekanshgupta6642

    11 ай бұрын

    @@abhishekkrthakur Where is it running? If not on your machine. Please let me know, very crucial.

  • @denzilstudios7072
    @denzilstudios7072 Жыл бұрын

    Now let's finetune it and do some RAG

  • @ChefDomein

    @ChefDomein

    Жыл бұрын

    Yes this please!🙏

  • @mitalicops8538

    @mitalicops8538

    2 ай бұрын

    Hi there what do mean by fine tuning and RAG plz can u explain it, i am a beginner.

  • @denzilstudios7072

    @denzilstudios7072

    2 ай бұрын

    @@mitalicops8538 Retrieval Augmented Generation (RAG) first searches through a bunch of documents using queries, which are basically questions or keywords. It then organizes all that info into a special kind of database called a vector database. When you ask a question using RAG, it quickly finds the best answer from that database and helps you generate new text based on it.

  • @frankbradford2869
    @frankbradford28693 ай бұрын

    This keeps giving an error message . When this happened to you, you said That you forgot to export the environment variable WHICH IS????

  • @abdokamr1393
    @abdokamr1393 Жыл бұрын

    Are it support Arabic language?

  • @lilianbaxan9543
    @lilianbaxan9543 Жыл бұрын

    You forgot to describe principal part of the item - server side ...

  • @shalabhgarg8225
    @shalabhgarg8225 Жыл бұрын

    It will be useful to have link for github repo

  • @abhishekkrthakur

    @abhishekkrthakur

    Жыл бұрын

    here you go: gist.github.com/abhishekkrthakur/a3d712c2709dcfbfa6a803fcfbcb5737

  • @youssefmellah2525
    @youssefmellah2525 Жыл бұрын

    Thank you for the great work!! But I'm facing the following error: requests.exceptions.ConnectionError: HTTPConnectionPool(host='localhost', port=3000): Max retries exceeded with url: / (Caused by NewConnectionError(': Failed to establish a new connection: [WinError 10061] Aucune connexion n’a pu être établi e car l’ordinateur cible l’a expressément refusée')) can you help please?

  • @koshalsingh9786

    @koshalsingh9786

    Жыл бұрын

    did that error got resolved?

  • @youssefmellah2525

    @youssefmellah2525

    Жыл бұрын

    @@koshalsingh9786 no not yet bro