goldfish-models / snd_arab_full

huggingface.co
Total runs: 107
24-hour runs: 0
7-day runs: 4
30-day runs: 90
Model's Last Updated: August 27 2024
text-generation

Introduction of snd_arab_full

Model Details of snd_arab_full

snd_arab_full

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the Sindhi (Arabic script) model trained on 459MB of data (all our data in the language), after accounting for an estimated byte premium of 1.59; content-matched text in Sindhi takes on average 1.59x 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: snd_arab is an individual language code. It is not contained in any macrolanguage codes contained in Goldfish (for script arab).

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: 124770816
  • Maximum sequence length: 512 tokens
  • Training text data (raw): 729.10MB
  • Training text data (byte premium scaled): 459.145MB
  • Training tokens: 114626048 (x10 epochs)
  • Vocabulary size: 50000
  • Compute cost: 5.84994711011328e+17 FLOPs or ~55.3 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 snd_arab_full on huggingface.co

107
Total runs
0
24-hour runs
1
3-day runs
4
7-day runs
90
30-day runs

More Information About snd_arab_full huggingface.co Model

More snd_arab_full license Visit here:

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

snd_arab_full huggingface.co

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

goldfish-models snd_arab_full online free

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

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

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

snd_arab_full install

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

snd_arab_full install url in huggingface.co:

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

Url of snd_arab_full

Provider of snd_arab_full huggingface.co

goldfish-models
ORGANIZATIONS

Other API from goldfish-models