goldfish-models / aze_latn_1000mb

huggingface.co
Total runs: 38
24-hour runs: 2
7-day runs: 12
30-day runs: 12
Model's Last Updated: August 27 2024
text-generation

Introduction of aze_latn_1000mb

Model Details of aze_latn_1000mb

aze_latn_1000mb

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the Azerbaijani (Latin script) model trained on 1000MB of data, after accounting for an estimated byte premium of 1.30; content-matched text in Azerbaijani takes on average 1.30x 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: aze_latn is a macrolanguage code. Individual language code azj_latn (North Azerbaijani) is included in Goldfish, although with less data.

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): 1298.79MB
  • Training text data (byte premium scaled): 1000.005MB
  • Training tokens: 233091584 (x10 epochs)
  • Vocabulary size: 50000
  • Compute cost: 1.189600434192384e+18 FLOPs or ~112.5 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 aze_latn_1000mb on huggingface.co

38
Total runs
2
24-hour runs
3
3-day runs
12
7-day runs
12
30-day runs

More Information About aze_latn_1000mb huggingface.co Model

More aze_latn_1000mb license Visit here:

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

aze_latn_1000mb huggingface.co

aze_latn_1000mb huggingface.co is an AI model on huggingface.co that provides aze_latn_1000mb's model effect (), which can be used instantly with this goldfish-models aze_latn_1000mb model. huggingface.co supports a free trial of the aze_latn_1000mb model, and also provides paid use of the aze_latn_1000mb. Support call aze_latn_1000mb model through api, including Node.js, Python, http.

goldfish-models aze_latn_1000mb online free

aze_latn_1000mb huggingface.co is an online trial and call api platform, which integrates aze_latn_1000mb's modeling effects, including api services, and provides a free online trial of aze_latn_1000mb, you can try aze_latn_1000mb online for free by clicking the link below.

goldfish-models aze_latn_1000mb online free url in huggingface.co:

https://huggingface.co/goldfish-models/aze_latn_1000mb

aze_latn_1000mb install

aze_latn_1000mb is an open source model from GitHub that offers a free installation service, and any user can find aze_latn_1000mb on GitHub to install. At the same time, huggingface.co provides the effect of aze_latn_1000mb install, users can directly use aze_latn_1000mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

aze_latn_1000mb install url in huggingface.co:

https://huggingface.co/goldfish-models/aze_latn_1000mb

Url of aze_latn_1000mb

Provider of aze_latn_1000mb huggingface.co

goldfish-models
ORGANIZATIONS

Other API from goldfish-models