RetroLemmy
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
thickertoofan@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 3 months ago

Microsoft KBLAM

www.microsoft.com

external-link
message-square
5
link
fedilink
13
external-link

Microsoft KBLAM

www.microsoft.com

thickertoofan@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 3 months ago
message-square
5
link
fedilink
A more efficient path to add knowledge to LLMs
www.microsoft.com
external-link
Introducing KBLaM, an approach that encodes and stores structured knowledge within an LLM itself. By integrating knowledge without retraining, it offers a scalable alternative to traditional methods.
alert-triangle
You must log in or register to comment.
  • SmokeyDope@lemmy.worldM
    link
    fedilink
    English
    arrow-up
    2
    ·
    3 months ago

    Looks promising, hope this ends up in an open source process that improved RAG type task.

    • thickertoofan@lemm.eeOP
      link
      fedilink
      English
      arrow-up
      1
      ·
      3 months ago

      It will, they have released a repo with code.

  • Autonomous User@lemmy.world
    link
    fedilink
    English
    arrow-up
    1
    ·
    edit-2
    3 months ago

    How might this impact VRAM requirements? I would also like to see a libre software implementation.

    • thickertoofan@lemm.eeOP
      link
      fedilink
      English
      arrow-up
      2
      ·
      3 months ago

      There is a repo they released.

  • MonsterBug@sh.itjust.worksM
    link
    fedilink
    English
    arrow-up
    1
    ·
    3 months ago

    Exciting!

LocalLLaMA@sh.itjust.works

localllama@sh.itjust.works

Subscribe from Remote Instance

Create a post
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !localllama@sh.itjust.works

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they’re still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 2 users / day
  • 101 users / week
  • 649 users / month
  • 1.37K users / 6 months
  • 2 local subscribers
  • 3.2K subscribers
  • 297 Posts
  • 1.47K Comments
  • Modlog
  • mods:
  • SkySyrup@sh.itjust.works
  • pax@sh.itjust.works
  • noneabove1182@sh.itjust.works
  • SmokeyDope@lemmy.world
  • MonsterBug@sh.itjust.works
  • BE: 0.19.11
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org