Is Falcon LLM the OpenAI Alternative? An Experimental Setup with LangChain

Поделиться
HTML-код
  • Опубликовано: 14 ноя 2024

Комментарии • 42

  • @daveebbelaar
    @daveebbelaar  Год назад +3

    👋🏻I'm launching a free community for those serious about learning Data & AI soon, and you can be the first to get updates on this by subscribing here: www.datalumina.io/newsletter

  • @user-wr4yl7tx3w
    @user-wr4yl7tx3w Год назад +10

    Can we try fine tuning the Falcon for future video

  • @oshodikolapo2159
    @oshodikolapo2159 Год назад +1

    Just what i was searching for. Thanks for this. bravo!

  • @sree_9699
    @sree_9699 Год назад

    Interesting! I was exploring the same thing just an hour ago on HF and ran into this video as I opened the RUclips. Good content.

  • @marcova10
    @marcova10 Год назад

    Thanks, Dave
    with some trials it seems that this version of falcon works for short questions,
    I am finding that in some cases the LLM spits several repeated sentences, may need some tweaking in the output to clean it up
    Great alternative for certain uses

  • @datanash8200
    @datanash8200 Год назад +1

    Perfect timing, need to implement some LLM for a work project 🙌

  • @aditunoe
    @aditunoe Год назад +1

    In the special_tokens_map.json file of the HF repo there are some special tokens defined that differ from what OpenAI or others use a little bit. Integrating those into a prompt template of the chains seemed to improve the results for me (Also wrote on example in the HF comments). Three interesting ones in particular:
    >>QUESTIONSUMMARY>ANSWER

  • @Esehe
    @Esehe Год назад

    @17:30 interesting how my OpenAI output/summary is different, than yours:
    " This article explains how to use Flowwise AI, an open source visual UI Builder, to quickly build
    large language models apps and conversational AI. It covers setting up Flowwise, connecting it to
    data, and building a conversational AI, as well as how to embed the agent in a Python file and run
    queries. It also shows how to use the agent to ask questions and get accurate results."

  • @esakkisundar
    @esakkisundar Год назад

    How to run the FalconModel locally. Does providing a key run the model in HuggingFace server?

  • @felixbrand7971
    @felixbrand7971 Год назад

    I’m sure this will be basic question, but where is the inference running here? Is it local, or is it on huggingface’s resources?

    • @vuktodorovic4768
      @vuktodorovic4768 Год назад

      That is what I wanted to ask. I mean I loaded this model into the google collab free tier and it took 15gb of ram and 14gb of GPU memory, I cant imagine what hardware you should have to run something like this locally. Also, I can't imagine that hugging face would give you their resources just like that. His setup seems very strange.

  • @Jake_McAllister
    @Jake_McAllister Год назад

    Hey Dave, love the video! How did you create your website, looks amazing bro 👌

  • @xXWillyxWonkaXx
    @xXWillyxWonkaXx Год назад +1

    Hey man, love your videos. Two questions:
    Q1. 11:50 are you talking about embedding?
    Q2. From your experience/deduction /observation of the LLM on huggingface, can you train a model like MosaicML MPT-7B, through in QLorRA in the mix and train it to be like GPT4 or even slightly better in terms of understanding/alignment - could using tree of thought mitigate or solve a small percentage of that?

    • @daveebbelaar
      @daveebbelaar  Год назад

      A1 - No I don't use embeddings in this example. Just plain text sent to the APIs
      A2 - Not sure about that

  • @KatarzynaHewelt
    @KatarzynaHewelt Год назад +1

    Thanks Dave for another great video! Do you know if I can perhaps download falcon locally and then use it privatelly - without HF API?

    • @daveebbelaar
      @daveebbelaar  Год назад

      Thanks Katarzyna! I am not sure about that.

  • @VaibhavPatil-rx7pc
    @VaibhavPatil-rx7pc Год назад

    Excellent detailed information

  • @bentouss3445
    @bentouss3445 Год назад +2

    Really great video on this hot topic of open llm vs closed ones...
    It will be really interesting to see how to self host a open llm to not go through any external inference API.

    • @daveebbelaar
      @daveebbelaar  Год назад

      Thanks! Yes that is very interesting indeed!

  • @luis96xd
    @luis96xd Год назад

    Great video, I have a doubt, what are the requirements to run locally Falcon-7B instruct? Can I use a CPU?

    • @fullcrum2089
      @fullcrum2089 Год назад +2

      15GB GPU Memory

    • @luis96xd
      @luis96xd Год назад

      @@fullcrum2089 Thank you so much! That's a Lot 😱

  • @ingluissantana
    @ingluissantana Год назад

    As always GREAT video!!!! Thanks!!!!

  • @GyroO7
    @GyroO7 Год назад

    I feel like using chunk size of 1000 with 200 overlaps will improve the results

  • @user-wr4yl7tx3w
    @user-wr4yl7tx3w Год назад

    Do you have a video on pre training an LLM?

  • @shakeebanwar4403
    @shakeebanwar4403 Год назад

    Can i run this 7b model without gpu my system ram is 32 gb

  • @PeterDrewSEO
    @PeterDrewSEO Год назад

    Great video mate, thank you!

  • @losing_interest_in_everything
    @losing_interest_in_everything Год назад

    Imagine combine it with Obsidian, Notion or other similar software

  • @mayorc
    @mayorc Год назад

    But don't you get a free amount of tokens for free that recharge every month using OpenAI, or not? So unless you go over the amount you shouldn't get charged.

  • @pragyanbhatt6200
    @pragyanbhatt6200 Год назад +1

    Nice tutorial Dave, but isn't it unfair to compare two models with different parameters count? falcon -7b has 7billion where as text-davinci-003 has almost 175 billion parameters?

    • @daveebbelaar
      @daveebbelaar  Год назад +1

      It's definitely unfair, but that's why it's interesting to see the performance of a much smaller, free to use model.

  • @ko-Daegu
    @ko-Daegu Год назад

    How are you runing a .py file as a jypeter Notebook on the side like that how are you taking each line inside it's one block to the side interactive
    this setup looks neat

    • @daveebbelaar
      @daveebbelaar  Год назад

      Check out this video: ruclips.net/video/zulGMYg0v6U/видео.html

    • @ko-Daegu
      @ko-Daegu Год назад

      @@daveebbelaar Merci

  • @fdarko1
    @fdarko1 Год назад

    I am new to Data science and want to know more about it to become a Pro. Please mentor me.

    • @daveebbelaar
      @daveebbelaar  Год назад

      Subscribe and check out the other videos on my channel ;)

  • @noelwos1071
    @noelwos1071 Год назад

    UNFAIR ADVANTAGE
    .What do you think, as a European citizen, would you have to sue Europe, which hinders the development of progress offered by artificial intelligence and thus causes enormous damage in Europe's lagging behind the whole world. isn't the EU a responsible institution

  • @deliciouspops
    @deliciouspops Год назад +1

    i like how degraded our society is

  • @VaibhavPatil-rx7pc
    @VaibhavPatil-rx7pc Год назад

    Excellent detailed information