Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Posts
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
bbunzeck 's Collections
Word learning in small LMs
German BabyLM
Small Language Models Also Work With Small Vocabularies
Fifty shapes of BLiMP: syntactic learning curves in LMs
GPT-wee: How Small Can a Small Language Model Really Get?

Small Language Models Also Work With Small Vocabularies

updated Jan 27

Models and evaluation data for our 2025 COLING paper (https://aclanthology.org/2025.coling-main.404/).

Upvote
-

  • bbunzeck/grapheme-llama

    Text Generation • Updated Sep 17, 2024 • 3.89k

  • bbunzeck/grapheme-llama-no-whitespace

    Text Generation • Updated Sep 17, 2024 • 3.88k

  • bbunzeck/phoneme-llama

    Text Generation • Updated Sep 17, 2024 • 3.87k

  • bbunzeck/phoneme-llama-no-whitespace

    Text Generation • Updated Sep 17, 2024 • 3.89k

  • bbunzeck/phoneme-babylm-10M

    Viewer • Updated Sep 8, 2024 • 3.92M • 4

  • bbunzeck/phoneme-babylm-100M

    Viewer • Updated Sep 8, 2024 • 15.8M • 9

  • bbunzeck/phoneme-blimp

    Viewer • Updated Sep 8, 2024 • 59.9k • 46

  • bbunzeck/rhyme-sentences

    Viewer • Updated Dec 2, 2024 • 400 • 13

  • bbunzeck/wug-words

    Viewer • Updated Dec 2, 2024 • 1k • 8

  • Small Language Models Also Work With Small Vocabularies: Probing the Linguistic Abilities of Grapheme- and Phoneme-Based Baby Llamas

    Paper • 2410.01487 • Published Oct 2, 2024
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs