goldfish-models / new_deva_full

huggingface.co
Total runs: 31
24-hour runs: 0
7-day runs: 3
30-day runs: 19
Model's Last Updated: August 27 2024
text-generation

Introduction of new_deva_full

Model Details of new_deva_full

new_deva_full

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the Newari (Devanagari script) model trained on 12MB of data (all our data in the language), after accounting for an estimated byte premium of 2.56; content-matched text in Newari takes on average 2.56x 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: new_deva is an individual language code. It is not contained in any macrolanguage codes contained in Goldfish (for script deva).

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): 31.86MB
  • Training text data (byte premium scaled): 12.445MB
  • Training tokens: 2927616 (x10 epochs)
  • Vocabulary size: 50000
  • Compute cost: 1.4934929965056e+16 FLOPs or ~1.4 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 new_deva_full on huggingface.co

31
Total runs
0
24-hour runs
0
3-day runs
3
7-day runs
19
30-day runs

More Information About new_deva_full huggingface.co Model

More new_deva_full license Visit here:

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

new_deva_full huggingface.co

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

goldfish-models new_deva_full online free

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

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

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

new_deva_full install

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

new_deva_full install url in huggingface.co:

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

Url of new_deva_full

Provider of new_deva_full huggingface.co

goldfish-models
ORGANIZATIONS

Other API from goldfish-models