bbc_latn_full

bbc_latn_full

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the <b>Batak Toba</b> (Latin script) model trained on 6MB of data (all our data in the language), after accounting for an estimated byte premium of 1.33; content-matched text in Batak Toba takes on average 1.33x 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: bbc_latn is an individual language 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): 8.63MB
• Training text data (byte premium scaled): 6.485MB
• Training tokens: 1846784 (x10 epochs)
• Vocabulary size: 50000
• Compute cost: 9421929381888000.0 FLOPs or ~0.9 NVIDIA A6000 GPU hours

Training datasets (percentages prior to deduplication):

• 98.53788%: MADLAD-400 (CommonCrawl)
• 1.46212%: IndoNLP

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},
}