Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,66 @@
+
+---
+license: apache-2.0
+language:
+- mlt
+datasets:
+- cis-lmu/Glot500
+- allenai/c4
+- legacy-datasets/wikipedia
+- allenai/nllb
+- oscar-corpus/OSCAR-2109
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- goldfish
+
+---
+
+# mlt_latn_1000mb
+
+Goldfish is a suite of monolingual language models trained for 350 languages.
+This model is the <b>Maltese</b> (Latin script) model trained on 1000MB of data, after accounting for an estimated byte premium of 1.09; content-matched text in Maltese takes on average 1.09x 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: mlt_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: 124770816
+* Maximum sequence length: 512 tokens
+* Training text data (raw): 1088.47MB
+* Training text data (byte premium scaled): 1000.005MB
+* Training tokens: 283158528 (x10 epochs)
+* Vocabulary size: 50000
+* Compute cost: 1.445110073524224e+18 FLOPs or ~136.6 NVIDIA A6000 GPU hours
+
+Training datasets (percentages prior to deduplication):
+* 94.92627%: [Glot500](https://huggingface.co/datasets/cis-lmu/Glot500), including [Wortschatz Leipzig Data](https://wortschatz.uni-leipzig.de/en/download), [MaCoCu](https://macocu.eu/), [MC4](https://huggingface.co/datasets/allenai/c4), [OSCAR](https://oscar-project.org/), [Wikipedia Hugging Face](https://huggingface.co/datasets/legacy-datasets/wikipedia)
+* 4.23828%: [NLLB (CommonCrawl and ParaCrawl)](https://huggingface.co/datasets/allenai/nllb)
+* 0.42133%: [OSCAR 2021/09](https://huggingface.co/datasets/oscar-corpus/OSCAR-2109)
+* 0.41412%: [Wikipedia 2023/08](https://dumps.wikimedia.org/)
+
+
+## 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},
+}
+```