goldfish-models / prs_arab_5mb

huggingface.co
Total runs: 94
24-hour runs: 0
7-day runs: 39
30-day runs: 82
Model's Last Updated: August 27 2024
text-generation

Introduction of prs_arab_5mb

Model Details of prs_arab_5mb

prs_arab_5mb

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the Dari (Arabic script) model trained on 5MB of data, after accounting for an estimated byte premium of 1.66; content-matched text in Dari takes on average 1.66x 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: prs_arab is an individual language code. Macrolanguage code fas_arab (Persian) 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) .

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. Details for this model specifically:

  • Architecture: gpt2
  • Parameters: 25455616
  • Maximum sequence length: 512 tokens
  • Training text data (raw): 8.32MB
  • Training text data (byte premium scaled): 5.005MB
  • Training tokens: 1207808 (x10 epochs)
  • Vocabulary size: 23971
  • Compute cost: 913441979105280.0 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},
}

Runs of goldfish-models prs_arab_5mb on huggingface.co

94
Total runs
0
24-hour runs
30
3-day runs
39
7-day runs
82
30-day runs

More Information About prs_arab_5mb huggingface.co Model

More prs_arab_5mb license Visit here:

https://choosealicense.com/licenses/apache-2.0

prs_arab_5mb huggingface.co

prs_arab_5mb huggingface.co is an AI model on huggingface.co that provides prs_arab_5mb's model effect (), which can be used instantly with this goldfish-models prs_arab_5mb model. huggingface.co supports a free trial of the prs_arab_5mb model, and also provides paid use of the prs_arab_5mb. Support call prs_arab_5mb model through api, including Node.js, Python, http.

goldfish-models prs_arab_5mb online free

prs_arab_5mb huggingface.co is an online trial and call api platform, which integrates prs_arab_5mb's modeling effects, including api services, and provides a free online trial of prs_arab_5mb, you can try prs_arab_5mb online for free by clicking the link below.

goldfish-models prs_arab_5mb online free url in huggingface.co:

https://huggingface.co/goldfish-models/prs_arab_5mb

prs_arab_5mb install

prs_arab_5mb is an open source model from GitHub that offers a free installation service, and any user can find prs_arab_5mb on GitHub to install. At the same time, huggingface.co provides the effect of prs_arab_5mb install, users can directly use prs_arab_5mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

prs_arab_5mb install url in huggingface.co:

https://huggingface.co/goldfish-models/prs_arab_5mb

Url of prs_arab_5mb

Provider of prs_arab_5mb huggingface.co

goldfish-models
ORGANIZATIONS

Other API from goldfish-models