What is Prompt Tuning?

Поділитися
Вставка
  • Опубліковано 21 гру 2024
  • Explore watsonx → ibm.biz/BdvxRp
    Prompt tuning is an efficient, low-cost way of adapting an AI foundation model to new downstream tasks without retraining the model and updating its weights. In this video, Martin Keen discusses three options for tailoring a pre-trained LLM for specialization, including: fine tuning, prompt engineering, and prompt tuning ... and contemplates a future career as a prompt engineer.
    Get started for free on IBM Cloud → ibm.biz/sign-u...
    Subscribe to see more videos like this in the future → ibm.biz/subscri...
    #ai #watsonx #llm

КОМЕНТАРІ • 73

  • @dominikzmudziak8340
    @dominikzmudziak8340 9 місяців тому +37

    Im stunned how Martin is able to write backwards on this board so efficiently

    • @pradachan
      @pradachan 9 місяців тому +24

      they just mirror the whole recording

    • @aidakostikova6889
      @aidakostikova6889 5 місяців тому +18

      haters will say that they just mirror the whole recording

    • @subusrable
      @subusrable 4 місяці тому +1

      seems you need to have that skill if you want to work at IBM

    • @dixit-publice
      @dixit-publice 3 місяці тому

      @@subusrable Almost right. What Martin is showing here is just the entry level. You actually have to be able to write in any direction. At IBM we call this 360-degree scribbling. And in any color, of course! (Patent pending - but we're considering to open-source the technology.)

    • @dixit-publice
      @dixit-publice 3 місяці тому

      At IBM Research we are even working on writing in n-dimensional space. Stay tuned.
      Agility and flexibility are key!

  • @Gordin508
    @Gordin508 Рік тому +37

    Really like these summarization videos on this channel. While they do not go into depth, I appreciate the overarching concepts being outlined and put into context in a clean way without throwing overly specific stuff in the mix.

    • @johndong4754
      @johndong4754 Рік тому

      Which channels would you recommend that go into more depth?

  • @WeiweiCheng
    @WeiweiCheng Рік тому +8

    Awesome content. Thanks for uploading.
    It's great that the video calls out the differences between soft prompting and hard prompting. While soft prompts offer more opportunities for performance tuning, practitioners often face the following issues:
    - Choosing between hard prompting with a more advanced, but closed, LLM versus soft prompting with an open-sourced LLM that is typically inferior in performance.
    - Soft prompting is model dependent, and hard prompting is less so.

  • @dharamindia563
    @dharamindia563 Рік тому +3

    Excellent broad explanation of complex AI topics. One can then deep dive once a basic understanding is achieved ! Thank you

  • @datagovernor
    @datagovernor Рік тому +4

    More important question, what type of smart/whiteboard are you using?? I love it!

  • @Asgardinho
    @Asgardinho Рік тому +5

    how do you get the AI to generate that tunable soft prompt?

  • @maxjesch
    @maxjesch Рік тому +14

    So how do I get to those "soft prompts"? Do you have to use prelabeled examples for that?

    • @cyberstorm45
      @cyberstorm45 5 місяців тому

      Soft Prompt example:
      I want to make a certain image in Stable Diffusion, but i don't know the exact prompt i need to type to generate that image, so i ask ChatGPT to generate that prompt for me (describing the characteristics of that image to be generated).
      ChatGPT outputs the prompt, in this case my Stable Diffusion soft prompt.

  • @SCP-GPT
    @SCP-GPT Рік тому +3

    You should make a guide on FlowGPT / Poe that delves into operators, delimiters, markdown, formatting, and syntax. I've been experimenting on these sites for a while, and the things they can do with prompts are mind-blowing.

    • @Atmatan
      @Atmatan 5 місяців тому

      Can you give some examples? I have yet to be impressed, but im notably hard to impress.

  • @8eck
    @8eck Рік тому +1

    This that soft prompt is basically a trainable parameters, which also undergoing backpropagation and its weights are updated? Just like LoRA method, where you attach new trainable parameters to the model and train only those new parameters.

  • @marc-oliviergiguere3290
    @marc-oliviergiguere3290 Рік тому +1

    Very concise and information, but tell me, what technology do you use to write backwards so fast? Do you flip the board in post-production?

    • @IBMTechnology
      @IBMTechnology  Рік тому

      Yes, see ibm.biz/write-backwards for details

  • @scifithoughts3611
    @scifithoughts3611 11 місяців тому

    Could you explain labeling done in fine tuning and prompt tuning?

  • @XavierPerales-zm4xx
    @XavierPerales-zm4xx 11 місяців тому

    Excellent job explaining key AI terms!

  • @apoorvvallabh2976
    @apoorvvallabh2976 Рік тому +1

    What data set for supervised learning is used in prompt tuning

  • @azadehesmaeili4402
    @azadehesmaeili4402 Рік тому

    Could you please outline the advantages and disadvantages of fine-tuning versus prompting in the context of large language models?

  • @Tititototo
    @Tititototo Рік тому +5

    Hi, nice talk by the way, but what about some examples of soft turning, i understand is human unreadable, but how exactly you achieve that ? by writing some code ? extra tools ? plugins ? thanks a lot for your reply :)

    • @sheepcraft7555
      @sheepcraft7555 Рік тому

      These are learnable parameters added on top the base language models. This is called soft tuning one of the example is prefix tuning. These parameters are learned.

  • @RobertoNascimento-kw6gy
    @RobertoNascimento-kw6gy 9 місяців тому

    Excelente video, bom trabalho

  • @tsunghan_yu
    @tsunghan_yu 6 місяців тому

    Why can't we use a decoder to convert the soft prompt to text and this ways it's interpretable? I don't quite understand

  • @BigBandoonthebeat
    @BigBandoonthebeat 6 місяців тому

    How do you make these soft prompts ?

  • @neail5466
    @neail5466 Рік тому +2

    Could you please explain a little detail about the strings of numbers how those are indexed? Are those some sort of abstraction that we fully understand!
    Very informative lecture is this one... Probably everyone should have a little expertise in prompt engineering skill in near future.

    • @Chris-se3nc
      @Chris-se3nc Рік тому

      There are other embedding models that can take strings of concepts and transform them into embedding vectors (string of numbers). You can store those in a number of vector databases.

  • @mikegioia9289
    @mikegioia9289 Рік тому

    How do you discover the correct soft prompts?

  • @Abishek_B
    @Abishek_B 5 місяців тому

    I'm doing a project where I need to categorise the transaction details from transactional SMS to be output in JSON type. Can I prompt tuning or prompt engr with hard prompt?

  • @ZyboroTown
    @ZyboroTown Рік тому

    What is unfancy design prompt?

  • @TimProvencio
    @TimProvencio Рік тому

    Does anyone know how they do these videos where it appears that they are writing on the screen. That is so neat!

  • @johndevan3505
    @johndevan3505 Рік тому

    A lot to unpack here. Great job explaining.
    I have one question about the difference between incontext learning and prompt tuning with hard prompts. Are they synonymous?

  • @russell_goodman
    @russell_goodman 5 місяців тому

    So is prompt engineering still a viable career (only because we’re in the infancy stages of widespread “commercial” use)…..of LLMs like ChatGPt.

  • @uniqueavi91
    @uniqueavi91 Рік тому

    crisp and informative

  • @yt-sh
    @yt-sh Рік тому +1

    funny & informative 👏👏👏

  • @pensiveintrovert4318
    @pensiveintrovert4318 5 місяців тому

    Why isn't this more popular if it actually works? All I see is LORAs and RL methods.

  • @mohslimani5716
    @mohslimani5716 Рік тому

    Thanks for the explanation, but still how could someone succeed in prompt engineering practically

  • @manojr4598
    @manojr4598 Рік тому

    We are trying to create a chatbot using OpenAI API and the response should be limited to the specific topic and it should not respond to the user queries which are not related to the topic. What is the best way to achieve this ? Prompt engineering or prompt tuning ?

  • @itdataandprocessanalysis3202
    @itdataandprocessanalysis3202 Рік тому +2

    A joke by ChatGPT:
    Why did the Large Language Model (LLM) turn down a job as a DJ?
    Because it thought "Prompt Tuning" meant it would have to constantly change the music!

  • @BigBandoonthebeat
    @BigBandoonthebeat 6 місяців тому

    Why don’t I see this anywhere if it’s better than normal prompts

  • @arpitqw1
    @arpitqw1 Рік тому

    not fully understood except- prompt tuning-prompt engineering- hard tuning-soft tuning. :P

  • @Betty__8a8v
    @Betty__8a8v 5 місяців тому

    Hello, I have some splendid news that will bring a smile to your face!

  • @rongarza9488
    @rongarza9488 10 місяців тому +2

    I learned Python in 2 months, great language. Then, I learned the SQLs that Python plays well with. Then, it hit me: AI is doing most of this work! So what is there for me and you to do? "My career may be over before it's begun". Yes, indeed UNLESS we can start using Python for regular business processing, like Accounts Receivable/Payable, Inventory Management, Order Processing, etc. In other words, we can't all be doing AI, especially when it, itself, is doing AI, cheaper, faster, and better.

    • @Atmatan
      @Atmatan 5 місяців тому

      God no. Please grow up soon so you can comprehend that python is killing the internet.

  • @fredrikt6980
    @fredrikt6980 7 місяців тому

    Really like all of Martins videos but this one only explains what prompt-tuning is not.

  • @badlaamaurukehu
    @badlaamaurukehu Рік тому +3

    Nomenclature is it's own problem.

  • @rajucmita
    @rajucmita Рік тому

    As a newbee how come I be pro in propmt engineering

  • @darkashes9953
    @darkashes9953 Рік тому

    IBM could go for the plunge and make a Quantum computer with 10 million Quantum computer chips with 1000 Qubits and optical circuits instead of just one chip.

  • @brcpimenta
    @brcpimenta 6 місяців тому

    Chuning

  • @YT-yt-yt-3
    @YT-yt-yt-3 10 місяців тому

    Soft peompring is confusing

  • @avinashpradhan5030
    @avinashpradhan5030 9 місяців тому

    🙂

  • @iramkumar78
    @iramkumar78 5 місяців тому

    I agree. AI soft prompts are not readable

  • @kaiskermani3724
    @kaiskermani3724 8 місяців тому

    "A string of numbers is worth a thousand words" tf does that even mean?

  • @samgoodwin89
    @samgoodwin89 Рік тому +1

    Is he writing backwards

  • @DK-ox7ze
    @DK-ox7ze Рік тому +6

    This is too abstract. Some concrete examples would have helped.

  • @generichuman_
    @generichuman_ Рік тому +28

    Wow, you managed to make an 8 minute video on prompt tuning without actually talking about what it is or how one would even begin to implement it. All I gleaned from this is that it has something to do with embeddings... Do better IBM...

    • @scifithoughts3611
      @scifithoughts3611 11 місяців тому +8

      I agree it’s a little obscure. I gave this a second watch through because your comment made me realize that I too wasn’t clear.
      Here is what I’ve noted:
      First step:
      Model creation: A model is created by training it from tons of data (very expensive to do)
      Because a model alone doesn’t work consistently at this point (racist, errors, hallucinations, toxic,…) it needs more work to be ready for the public. To make it ready one of the three strategies are used: fine tuning, prompt engineering, or prompt tuning with soft prompts. (All three could be used as well, I’ve read papers about such cases.)
      Fine tuning :
      Give you have a model, now you create examples about the domain the LLM will represent. The examples are labeled to help the model know what’s is going on. This strategy is labor intensive. (Labeling is another whole area to read up on.)
      Prompt engineering:
      Humans design prompts in a human language (explain to the model how to behave). Example: when I tell you a word in English, you respond with the word in French.
      Prompt tuning using soft prompts:
      Soft prompts are created by the AI using fine tuning data. These prompts are encoded (not human readable) into a vector.
      The above is the first six minutes of the video. Next the lecturer show these three applications by adding them to the box picture. This is confusing because it seems like he is applying all three strategies but then concludes that prompt tuning gets the best results. So I guess he is saying use prompt tuning.
      Since AiML is a new field, I think people will be applying many different strategies in order to get their models to work properly. And this is just scratching the surface. Every few months, people will come up with other strategies that improve the situation. 10 years from now a bunch of these strategies will be discarded and there will be other new ones. The field of ML is defining their design patterns. Pattern books will be written as solutions mature. Prompt engineering and prompt tuning are the two patterns he talks about.
      I hope that helps. Thinking this through has certainly helped me so thanks for the prompt. 😊

    • @chavruta2000
      @chavruta2000 11 місяців тому +1

      yes. this is incredibly generic and communicates very little considering this is supposed to be from a communication theory expert.

    • @RajatKumar-oy9mw
      @RajatKumar-oy9mw 9 місяців тому

      Totally agrees..

    • @pensiveintrovert4318
      @pensiveintrovert4318 5 місяців тому

      I got one useful tidbit. That I have to stick the soft prompt into the embedding layer. How? Also unclear.

  • @DJZG
    @DJZG 6 місяців тому

    Shame not a single real-world example of prompt tuning isn't provided. I guess this video isn't about that kind of detail?

  • @bongimusprime7981
    @bongimusprime7981 Рік тому +1

    ChatGPT is not an LLM lol