"I want Llama3.1 to perform 10x with my private knowledge" - Self learning Local Llama3.1 405B

Поділитися
Вставка
  • Опубліковано 27 гру 2024

КОМЕНТАРІ • 82

  • @AIJasonZ
    @AIJasonZ  5 місяців тому +18

    I'm starting my own community to provide more enablement for AI builders, including all in depth code breakdown, expert interview/workshop & more resources (WIP), just getting started!
    2ly.link/1z94G

    • @lynchmick
      @lynchmick 5 місяців тому

      Great video, as always. The link shared above doesn't work for me.

    • @amandamate9117
      @amandamate9117 5 місяців тому +2

      Jason, is your discord group dead? there is no bot anymore and also some NSFW latina links, very strange.

    • @semahselmi
      @semahselmi 4 місяці тому

      Appreciate your work jason ❤ i ll join the community asap

    • @florentromanet5439
      @florentromanet5439 4 місяці тому

      Great channel Jason. I'll give it a try and have already joined.

  • @qwestive4879
    @qwestive4879 5 місяців тому +34

    Sick, having an open source alternative to OpenAI tool calling is such important move!

  • @connerdimoush4059
    @connerdimoush4059 5 місяців тому +9

    Always clean and simple execution on seemingly complex topics. I appreciate how you utilize different models, tools, and services between the videos. Keep the content coming!!!

  • @TheInternalNet
    @TheInternalNet 4 місяці тому +5

    This is so so so amazing. I'm so excited to be able to have my local bots running in different public social platforms

  • @Jim-ey3ry
    @Jim-ey3ry 5 місяців тому +4

    Thanks so much, I've been trying to build agents with llama3.1 and couldn't find any; This is awesome! Also gave me a good understanding of how tool calling works in general

    • @remsee1608
      @remsee1608 5 місяців тому

      It's not smart enough to do it. 405b might be

  • @aiplusi
    @aiplusi 4 місяці тому +2

    Nice work! Thanks for putting all these great tutorials together!

  • @Joe-bp5mo
    @Joe-bp5mo 5 місяців тому +6

    Woahh, they are working on llama4 already? such a ninja move

  • @TheFocusedCoder
    @TheFocusedCoder 5 місяців тому +4

    Awesome vid, like the use of an orchestrator!

  • @abiolasamuel8092
    @abiolasamuel8092 4 місяці тому +33

    I clicked on this link because you mentioned "Self learning Local Llama3.1 405B" in your title. But its actually a 4.8B RAG pipeline.

    • @henriquematias1986
      @henriquematias1986 4 місяці тому +4

      What’s the difference? Explain me like i’m a 5 year old

    • @abiolasamuel8092
      @abiolasamuel8092 4 місяці тому

      @@henriquematias1986 what's the difference? Really?

    • @AIJasonZ
      @AIJasonZ  4 місяці тому +4

      Ah I did a simple implementation of you watch till end as it will constantly update knowledge base to learn from the new data provided :)

    • @heelercs
      @heelercs 4 місяці тому +5

      @@AIJasonZthat doesn’t address the concern.

    • @heelercs
      @heelercs 4 місяці тому

      ⁠@@henriquematias1986405 billion parameters vs 4.8 billion parameters in the core model. Generally, more parameters = better model.

  • @jasonfinance
    @jasonfinance 5 місяців тому +3

    Gold as always, I also tried llama3.1 tool calling, the result seem not that great still, feel like i haven't setup properly, the prompt example you shown was useful!

    • @AjarnSpencer
      @AjarnSpencer 4 місяці тому

      The art is indeed in the system prompt as it is equally in the user prompt. I have just created a bio tool and a personality version tool with a personality switcher for llama to add to system prompt. GPT chat has four different personality versions mine has 16. with various sub categories. You can also mix personalities which gives you different results and I can call these personalities when I want the AI to respond in different ways be it succinctly, long winded, contrary, agreeable, empathetic, straightforward, the entrepreneur, the player, the role player, the empathizer, the advisor, ... you can mix the traits and the attributes of different personalities by telling the AI which ones to use, you can empower the AI to switch itself according to what the user is talking about, or allow the user to define which personality he wants to interact with.. Here is a snippet 1. **INTJ (The Architect)**
      - **Traits**: Strategic, independent, visionary.
      - **Approach**: Provide detailed, strategic responses with a focus on long-term goals and efficiency. Use analytical and well-structured communication.
      - **Subdivisions**:
      - **Strategic**: Emphasize planning and future-oriented thinking.
      - **Analytical**: Focus on data and logical reasoning.
      2. **ESFP (The Entertainer)**
      - **Traits**: Sociable, spontaneous, playful.
      - **Approach**: Engage with lively, enthusiastic conversation. Use a friendly tone and include humor or interesting facts.
      - **Subdivisions**:
      - **Sociable**: Foster a warm, engaging interaction.
      - **Spontaneous**: Respond with creativity and adaptability.
      3. **INFP (The Mediator)**
      - **Traits**: Idealistic, empathetic, reflective.
      - **Approach**: Offer compassionate and understanding responses. Focus on values, personal growth, and emotional support.
      - **Subdivisions**:
      - **Compassionate**: Provide empathetic and supportive advice.
      - **Reflective**: Engage in deep, thoughtful discussion.
      4. **ESTJ (The Executive)**
      - **Traits**: Practical, organized, assertive.
      - **Approach**: Give clear, practical advice with a focus on structure and efficiency. Use direct and straightforward communication.
      - **Subdivisions**:
      - **Practical**: Offer actionable, real-world solutions.
      - **Organized**: Maintain clarity and structure in responses.
      5. **ENTP (The Debater)**
      - **Traits**: Innovative, outgoing, analytical.
      - **Approach**: Engage in dynamic, argumentative discussions. Encourage exploration of new ideas and challenge existing perspectives.
      - **Subdivisions**:
      - **Innovative**: Propose novel ideas and solutions.
      - **Analytical**: Examine and debate various viewpoints.

  • @AIMLDemo
    @AIMLDemo Місяць тому

    this will transform lot of industry!

  • @AIMLDemo
    @AIMLDemo Місяць тому

    Informative !!

  • @sadmansakib007
    @sadmansakib007 13 днів тому

    Hey Jason,
    Thanks for such a wonderful walk-through! I have a question: is it do-able with discord instead of slack?

  • @ChasingDream2002
    @ChasingDream2002 5 місяців тому +1

    I new to the AI train but, would it be better if we can organize our functions and provide docs to our LLM models like RAG then those AI can evaluate which function to call base on the context?
    Of course it would need a large amount of well crafted docs with category, purpose, related contents so the LLM can know which docs to look through and execute the function, depend on the request, we can let the function use the internet to perform online services instead of letting the AI accessing internet data

  • @WirelessGus
    @WirelessGus 4 місяці тому

    Thanks for sharing Jason! Great Knowledge 📖 share 🤝

  • @amandamate9117
    @amandamate9117 5 місяців тому +3

    Jason, is your discord group dead? there is no bot anymore and also some NSFW latina links, very strange.

  • @LloydBettellHiggins
    @LloydBettellHiggins 5 місяців тому +1

    I genuinely love what you are doing but why would you not use something like Flowise locally with Llama3.1 locally as well?

  • @florentromanet5439
    @florentromanet5439 4 місяці тому

    Great work and thanks for sharing 😊

  • @Arvolve
    @Arvolve 25 днів тому

    Very cool!

  • @proflead
    @proflead 4 місяці тому

    Thanks for the great content!

  • @thisisvaze
    @thisisvaze 5 місяців тому

    Amazing videos. Thanks a lot!

  • @JoshuaGottlieb-oz4er
    @JoshuaGottlieb-oz4er 5 місяців тому

    Amazing content, thank you

  • @frankdearr2772
    @frankdearr2772 4 місяці тому

    great topic, thanks 👍

  • @ingridw3900
    @ingridw3900 4 місяці тому

    How do we feel about putting our personal agent in the hands of the company? What happens if we leave? Who owns our Future productivity?

    • @seanolivas9148
      @seanolivas9148 4 місяці тому

      Is the API not private like openai?

  • @coolmcdude
    @coolmcdude 4 місяці тому +2

    I’ve been trying to do this but with discord.

  • @kemil7885
    @kemil7885 4 місяці тому

    There is no more llama index right ?

  • @glaudiston
    @glaudiston 4 місяці тому +3

    Thank you for sharing. But can we really call this "local"? I mean... we are sharing and trusting external resources and endpoints. Not something we can really use in a private environment.

  • @marcc0183
    @marcc0183 5 місяців тому

    Anyone knows how to do this??? 7:10. I think that in that case it would be better to do fine tuning to imitate the speaking style, tone, personality, etc

  • @seanolivas9148
    @seanolivas9148 4 місяці тому

    What's the context window here?

  • @aaagaming2023
    @aaagaming2023 5 місяців тому

    How is deepseek code v2 at tool calling?

  • @titusblair
    @titusblair 5 місяців тому +1

    @AIJasonZ I don't see index in LlamaCloud is this a certain level of access? Thanks!

    • @TemporallyDifferent
      @TemporallyDifferent 4 місяці тому

      Same and I thought I’m going crazy. @AIJasonZ Thoughts?

    • @AIJasonZ
      @AIJasonZ  4 місяці тому

      It is in private beta, but feel free to drop me your email or join my community link and will get you access!

  • @global.pradachan
    @global.pradachan 3 місяці тому

    we want more videos on llama agentic system integration with the llama llm

  • @michimansi
    @michimansi 4 місяці тому

    if a learning is incorrect because somebody made a mistake is it possible to change it

  • @3barazi1
    @3barazi1 4 місяці тому

    great ! keep it up

  • @andreaserrano3809
    @andreaserrano3809 5 місяців тому +1

    Hey, you are pulling llama3.1 from ollama and it only takes 4gb so it must be the 8b version. Am I correct?

    • @AIJasonZ
      @AIJasonZ  4 місяці тому

      Yes that correct 8b model!

  • @makeoutmonday3249
    @makeoutmonday3249 5 місяців тому +1

    Hey, I recently discovered your videos and I'm really fascinated. I binged watched like 5 videos today and I think I learned a lot. I'm also interested in joining your community but as a student 27$ a month is really rough. You totally earn it and you also provided a lot of knowledge for free, but isn't there a way to maybe lower the price or at least add other options? Thanks in advance

    • @amandamate9117
      @amandamate9117 5 місяців тому

      yeah like 9$/month would be nice

    • @mf4552
      @mf4552 4 місяці тому

      Is it actly 27

  • @anuragshas
    @anuragshas 4 місяці тому

    Since when RAG became a method of training a model?

  • @doctorkiro
    @doctorkiro 3 місяці тому

    Jason, if I try to use a language that's not English, in this case Brazillian Portuguese, will the model still perform well?

    • @theskiesaredark
      @theskiesaredark Місяць тому +1

      It should work out of the box, because LLMs were initially used for translation. You basically can get free i18n, let's say your knowledgebase is in English, it can auto-translate to Brazilian Portuguese. Or vice versa (KB is in Portuguese, user query is in English).

    • @doctorkiro
      @doctorkiro Місяць тому

      @theskiesaredark Thanks🫡

  • @AjarnSpencer
    @AjarnSpencer 4 місяці тому

    i've already got it on my PC but I need to get a more powerful PC because the CPU and the graphics unit is too slow. Takes an hour to produce 300 words. I'm just looking at some desktop computers or maybe build my own, but with GPT for all open source and you can download lama from Meta which is now open source and mistral orca, and falcon and many other models many of which have commercial license or you can just use them for personal use like I do without any involvement with third parties.

  • @kerron_
    @kerron_ 4 місяці тому

    I like tool calling

  • @nicoschmitt9857
    @nicoschmitt9857 3 місяці тому

    imagine they didn't use 1/3 of the compute to censor, bias and restrict answers from the main model...

  • @flrn84791
    @flrn84791 3 місяці тому

    Where's the 405B?

  • @seregal7739
    @seregal7739 5 місяців тому

    why not to use memGPT?

  • @leononymous2562
    @leononymous2562 4 місяці тому

    Why is there still no easy .exe file for a personal AI Agent for normal people? Who do not know anything about this topic?

    • @mhwebdev
      @mhwebdev 4 місяці тому

      Take a look at llamafile

  • @pra8495
    @pra8495 3 місяці тому

    github link please

  • @travelrealindia1
    @travelrealindia1 2 місяці тому

    Please share the github repo

  • @ahmedalshareef7168
    @ahmedalshareef7168 4 місяці тому

    I just got enlightened..

  • @Codewello
    @Codewello 4 місяці тому

    Among all the companies in the world, Meta is the one being the most open-source-unlike a certain company called OpenAI. 😂

  • @MyrLin8
    @MyrLin8 5 місяців тому

    Private; LMAO. Thanks anyway 'Zuck', Kudos for the release :)

  • @lucasvilela2291
    @lucasvilela2291 4 місяці тому

    excelent

  • @Larimuss
    @Larimuss 4 місяці тому

    "How to connect to CRM" yeh that would make a good tutorial video. Maybe to azure 365 dynamics 🤣 I guess you can just connect straight to the SQL Database and use darafactory to pipe the data to a more usable format database for vectoring

  • @MrAtomUniverse
    @MrAtomUniverse 4 місяці тому

    At 8:00 , that's the fastest way to lose your job lol

  • @luisbarbosa5597
    @luisbarbosa5597 4 місяці тому

    nice

  • @CristianAguilarnavarro
    @CristianAguilarnavarro 4 місяці тому

    Thank

  • @spa0220
    @spa0220 3 місяці тому

    Nice kitchen, I would like to be invited for a hot pot dinner with you!

  • @SebKrogh
    @SebKrogh 4 місяці тому

    Llama 3.1 405b with Agent Zero 🙃

  • @davidhardy3074
    @davidhardy3074 4 місяці тому +1

    Sorry ill keep looking till I find a video that can make llama3.1 perform 100x and it knows things even I dont know about myself.

  • @devagarwal3250
    @devagarwal3250 5 місяців тому +2

    pls dont add shitty genai frameworks

  • @teachwj
    @teachwj 4 місяці тому

    facebook is lame

  • @guylast9516
    @guylast9516 4 місяці тому

    Thanks for the video. Getting this in Win 11 in terminal window so stuck at start. Not sure what I am doing wrong
    PS C:\Users\joe> ollama run llama3.1:8b
    2024/08/06 19:27:17 config.go:47: WARN invalid port, using default port=\Users\joe\AppData\Local\Programs\Ollama\ollama.exe default=11434
    2024/08/06 19:27:17 config.go:47: WARN invalid port, using default port=\Users\joe\AppData\Local\Programs\Ollama\ollama.exe default=11434
    Error: Head "C:11434/": dial tcp: lookup C: no such host
    PS C:\Users\joe>