--- license: apache-2.0 language: - chi - zho - nan datasets: - cis-lmu/Glot500 - legacy-datasets/wikipedia - allenai/MADLAD-400 library_name: transformers pipeline_tag: text-generation tags: - goldfish --- # nan_latn_5mb Goldfish is a suite of monolingual language models trained for 350 languages. This model is the Min Nan Chinese (Latin script) model trained on 5MB of data, after accounting for an estimated byte premium of 1.15; content-matched text in Min Nan Chinese takes on average 1.15x 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: nan_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://github.com/tylerachang/goldfish/blob/main/goldfish_paper_20240815.pdf). 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/model_details.json. All models are trained with a [CLS] (same as [BOS]) token prepended, and a [SEP] (same as [EOS]) token separating sequences. Details for this model specifically: * Architecture: gpt2 * Parameters: 39087104 * Maximum sequence length: 512 tokens * Training text data (raw): 5.74MB * Training text data (byte premium scaled): 5.005MB * Training tokens: 1916416 (x10 epochs) * Vocabulary size: 50000 * Compute cost: 1449598601134080.0 FLOPs or ~0.1 NVIDIA A6000 GPU hours Training datasets (percentages prior to deduplication): * 49.98250%: [Glot500](https://huggingface.co/datasets/cis-lmu/Glot500), including [Wortschatz Leipzig Data](https://wortschatz.uni-leipzig.de/en/download), [Wikipedia Hugging Face](https://huggingface.co/datasets/legacy-datasets/wikipedia) * 42.06803%: [Wikipedia 2023/08](https://dumps.wikimedia.org/) * 7.94947%: [MADLAD-400 (CommonCrawl)](https://huggingface.co/datasets/allenai/MADLAD-400) ## 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}, } ```