Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,64 @@
+
+---
+license: apache-2.0
+language:
+- xal
+datasets:
+- allenai/MADLAD-400
+- oscar-corpus/OSCAR-2109
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- goldfish
+
+---
+
+# xal_cyrl_5mb
+
+Goldfish is a suite of monolingual language models trained for 350 languages.
+This model is the <b>Kalmyk</b> (Cyrillic script) model trained on 5MB of data, after accounting for an estimated byte premium of 1.72; content-matched text in Kalmyk takes on average 1.72x 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: xal_cyrl 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 cyrl).
+
+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): 8.62MB
+* Training text data (byte premium scaled): 5.005MB
+* Training tokens: 1236992 (x10 epochs)
+* Vocabulary size: 50000
+* Compute cost: 935949710131200.0 FLOPs or ~0.1 NVIDIA A6000 GPU hours
+
+Training datasets (percentages prior to deduplication):
+* 74.88105%: [Languages of Russia](http://web-corpora.net/wsgi3/minorlangs/download)
+* 21.64138%: [MADLAD-400 (CommonCrawl)](https://huggingface.co/datasets/allenai/MADLAD-400)
+* 3.15243%: [Wikipedia 2023/08](https://dumps.wikimedia.org/)
+* 0.23428%: [OSCAR 2021/09](https://huggingface.co/datasets/oscar-corpus/OSCAR-2109)
+* 0.09086%: [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},
+}
+```