KTE GL - Lemmy
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
pepperfree@sh.itjust.works to LocalLLaMA@sh.itjust.worksEnglish · 8 days ago

When DeepSeek V4 and R2?

sh.itjust.works

message-square
26
fedilink
185

When DeepSeek V4 and R2?

sh.itjust.works

pepperfree@sh.itjust.works to LocalLLaMA@sh.itjust.worksEnglish · 8 days ago
message-square
26
fedilink
  • Omega@discuss.online
    link
    fedilink
    English
    arrow-up
    13
    ·
    8 days ago

    I wonder if a good fine tuned model beats every general purpose LLM if you need it for a really specific purpose

    • laz@lemmy.dbzer0.com
      link
      fedilink
      English
      arrow-up
      21
      ·
      8 days ago

      Yes it does

    • kata1yst@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      8
      ·
      8 days ago

      Of course, and this is why the new hotness is a Mixture of Experts for one model that is effectively a bunch of experts arguing over the answer, or else on a different scale there’s the Combination of Agents where different specialized agents perform specialized tasks.

    • pepperfree@sh.itjust.worksOP
      link
      fedilink
      English
      arrow-up
      1
      ·
      8 days ago

      There is new project which they share fine-tuned modernbert on some task. Here is the org https://huggingface.co/adaptive-classifier

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: [email protected]

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.

  • 38 users / day
  • 125 users / week
  • 593 users / month
  • 1.44K users / 6 months
  • 1 local subscriber
  • 3.55K subscribers
  • 150 Posts
  • 822 Comments
  • Modlog
  • mods:
  • MonsterBug@sh.itjust.works
  • SmokeyDope@lemmy.world
  • SkySyrup@sh.itjust.works
  • pax@sh.itjust.works
  • noneabove1182@sh.itjust.works
  • BE: 0.19.10
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org