|
|
| --- |
| license: apache-2.0 |
| language: |
| - mhr |
| - chm |
| datasets: |
| - cis-lmu/Glot500 |
| - legacy-datasets/wikipedia |
| - oscar-corpus/OSCAR-2109 |
| library_name: transformers |
| pipeline_tag: text-generation |
| tags: |
| - goldfish |
| - arxiv:2408.10441 |
| --- |
| |
| # mhr_cyrl_full |
|
|
| Goldfish is a suite of monolingual language models trained for 350 languages. |
| This model is the <b>Eastern Mari</b> (Cyrillic script) model trained on 27MB of data (all our data in the language), after accounting for an estimated byte premium of 1.81; content-matched text in Eastern Mari takes on average 1.81x 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: mhr_cyrl is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. Macrolanguage code chm_cyrl (Mari (Russia)) is included in Goldfish. Consider using that model depending on your use case. |
|
|
| 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: 124770816 |
| * Maximum sequence length: 512 tokens |
| * Training text data (raw): 50.43MB |
| * Training text data (byte premium scaled): 27.865MB |
| * Training tokens: 6580224 (x10 epochs) |
| * Vocabulary size: 50000 |
| * Compute cost: 3.3571845439488e+16 FLOPs or ~3.2 NVIDIA A6000 GPU hours |
| |
| Training datasets (percentages prior to deduplication): |
| * 85.57926%: [Languages of Russia](http://web-corpora.net/wsgi3/minorlangs/download) |
| * 7.02298%: [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/), [Wikipedia Hugging Face](https://huggingface.co/datasets/legacy-datasets/wikipedia) |
| * 4.37537%: [Wikipedia 2023/08](https://dumps.wikimedia.org/) |
| * 2.95016%: [OSCAR 2021/09](https://huggingface.co/datasets/oscar-corpus/OSCAR-2109) |
| * 0.07223%: [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}, |
| } |
| ``` |
| |
