CoolFace
Modelpublic

goldfish-models/wln_latn_full

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes32downloads
Model Card

license: apache-2.0 language:

  • —wln datasets:
  • —cis-lmu/Glot500
  • —legacy-datasets/wikipedia
  • —allenai/MADLAD-400
  • —oscar-corpus/OSCAR-2109 libraryname: transformers pipelinetag: text-generation tags:
  • —goldfish
  • —arxiv:2408.10441 ---

wlnlatnfull

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the <b>Walloon</b> (Latin script) model trained on 102MB of data (all our data in the language), after accounting for an estimated byte premium of 1.22; content-matched text in Walloon takes on average 1.22x as many UTF-8 bytes to encode as English. The Goldfish models are trained primarily for comparability across languages and for low-resource languages; Goldfish performance for high-resource languages is not designed to be comparable with modern large language models (LLMs).

Note: wlnlatn is an [individual language](https://iso639-3.sil.org/codetables/639/data) code. It is not contained in any macrolanguage codes contained in Goldfish (for script latn).

All training and hyperparameter details are in our paper, Goldfish: Monolingual Language Models for 350 Languages (Chang et al., 2024).

Training code and sample usage: https://github.com/tylerachang/goldfish

Sample usage also in this Google Colab: link

Model details:

To access all Goldfish model details programmatically, see https://github.com/tylerachang/goldfish/blob/main/model_details.json. All models are trained with a [CLS] (same as [BOS]) token prepended, and a [SEP] (same as [EOS]) token separating sequences. For best results, make sure that [CLS] is prepended to your input sequence (see sample usage linked above)! Details for this model specifically:

  • —Architecture: gpt2
  • —Parameters: 124770816
  • —Maximum sequence length: 512 tokens
  • —Training text data (raw): 124.67MB
  • —Training text data (byte premium scaled): 102.325MB
  • —Training tokens: 29091328 (x10 epochs)
  • —Vocabulary size: 50000
  • —Compute cost: 1.485053263872e+17 FLOPs or ~14.0 NVIDIA A6000 GPU hours

Training datasets (percentages prior to deduplication):

Citation

If you use this model, please cite:

@article{chang-etal-2024-goldfish,
  title={Goldfish: Monolingual Language Models for 350 Languages},
  author={Chang, Tyler A. and Arnett, Catherine and Tu, Zhuowen and Bergen, Benjamin K.},
  journal={Preprint},
  year={2024},
  url={https://www.arxiv.org/abs/2408.10441},
}