Hugging Face's logo

goldfish-models
/
kaa_latn_5mb

Text Generation
Transformers
PyTorch
Kara-Kalpak
gpt2
goldfish
text-generation-inference
Inference Endpoints
Model card Files Community
kaa_latn_5mb / README.md
goldfish-models's picture
goldfish-models
Upload README.md with huggingface_hub
6298a23 verified
preview code
|
raw
history blame contribute delete
2.97 kB
metadata
license: apache-2.0
language:
  - kaa
datasets:
  - allenai/MADLAD-400
  - cis-lmu/Glot500
  - legacy-datasets/wikipedia
library_name: transformers
pipeline_tag: text-generation
tags:
  - goldfish
  - arxiv:2408.10441

kaa_latn_5mb

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the Kara-Kalpak (Latin script) model trained on 5MB of data, after accounting for an estimated byte premium of 1.23; content-matched text in Kara-Kalpak 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: This language is available in Goldfish with other scripts (writing systems). See: kaa_cyrl.

Note: kaa_latn is an individual language 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).

Training code and sample usage: https://github.com/tylerachang/goldfish

Sample usage also in this Google Colab: link

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): 6.14MB
  • Training text data (byte premium scaled): 5.005MB
  • Training tokens: 1245184 (x10 epochs)
  • Vocabulary size: 50000
  • Compute cost: 942148052582400.0 FLOPs or ~0.1 NVIDIA A6000 GPU hours

Training datasets (percentages prior to deduplication):

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},
}