--- license: apache-2.0 language: - pms datasets: - cis-lmu/Glot500 - legacy-datasets/wikipedia - oscar-corpus/OSCAR-2109 library_name: transformers pipeline_tag: text-generation tags: - goldfish - arxiv:2408.10441 --- # pms_latn_5mb Goldfish is a suite of monolingual language models trained for 350 languages. This model is the <b>Piemontese</b> (Latin script) model trained on 5MB of data, after accounting for an estimated byte premium of 1.23; content-matched text in Piemontese takes on average 1.23x 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: pms_latn is an [individual language](https://iso639-3.sil.org/code_tables/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)](https://www.arxiv.org/abs/2408.10441). Training code and sample usage: https://github.com/tylerachang/goldfish Sample usage also in this Google Colab: [link](https://colab.research.google.com/drive/1rHFpnQsyXJ32ONwCosWZ7frjOYjbGCXG?usp=sharing) ## 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: 39087104 * Maximum sequence length: 512 tokens * Training text data (raw): 6.13MB * Training text data (byte premium scaled): 5.005MB * Training tokens: 1628672 (x10 epochs) * Vocabulary size: 50000 * Compute cost: 1231184509009920.0 FLOPs or ~0.1 NVIDIA A6000 GPU hours Training datasets (percentages prior to deduplication): * 55.69647%: [Glot500](https://huggingface.co/datasets/cis-lmu/Glot500), including [Wortschatz Leipzig Data](https://wortschatz.uni-leipzig.de/en/download), [OSCAR](https://oscar-project.org/), [Tatoeba](https://tatoeba.org/en/), [W2C](https://lindat.mff.cuni.cz/repository/xmlui/handle/11858/00-097C-0000-0022-6133-9), [Wikipedia Hugging Face](https://huggingface.co/datasets/legacy-datasets/wikipedia) * 37.63180%: [Wikipedia 2023/08](https://dumps.wikimedia.org/) * 6.63122%: [OSCAR 2021/09](https://huggingface.co/datasets/oscar-corpus/OSCAR-2109) * 0.04052%: [Tatoeba](https://tatoeba.org/en/) ## 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}, } ```