this post was submitted on 28 Sep 2023
33 points (100.0% liked)

Technology

59219 readers
2836 users here now

This is a most excellent place for technology news and articles.

Our Rules

  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each another!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 1 year ago
MODERATORS
L3s@lemmy.world
L3s@fry.gs
L4s@fry.gs
L4s@lemmy.world
enu@lemmy.world
33
An Analysis of DeepMind's 'Language Modeling Is Compression' Paper (codeconfessions.substack.com)
submitted 1 year ago by abhi9u@lemmy.world to c/technology@lemmy.world
10 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] drre@feddit.de 2 points 1 year ago (3 children)

does anyone know whether these results were obtained while taking the size of the dictionary into account?

[–] AbouBenAdhem@lemmy.world 3 points 1 year ago (1 children)

It looks like they did it both ways (“raw rate” vs “adjusted rate”):

In the case of the adjusted compression rate, the model's size is also added to the compressed size, i.e., it becomes (compressed size + number of model parameters) / raw size. This metric allows us to see the impact of model parameters on the compression performance. A very large model might be able to compress the data better compared to a smaller model, but when its size is taken into account, the smaller model might be doing better. This metric allows us to see that.

[–] abhi9u@lemmy.world 2 points 1 year ago

Yes. They also mention that using such large models for compression is not practical because their size thwarts any amount of data you might want to compress. But this result gives a good picture into how generalized such large models are, and how well they are able to predict the next tokens for image/audio data at a high accuracy.

load more comments (1 replies)