goldfish-models / epo_latn_1000mb

huggingface.co
Total runs: 19
24-hour runs: 0
7-day runs: -2
30-day runs: -3
Model's Last Updated: August 27 2024
text-generation

Introduction of epo_latn_1000mb

Model Details of epo_latn_1000mb

epo_latn_1000mb

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the Esperanto (Latin script) model trained on 1000MB of data, after accounting for an estimated byte premium of 1.00; content-matched text in Esperanto takes on average 1.00x 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: epo_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. Details for this model specifically:

  • Architecture: gpt2
  • Parameters: 124770816
  • Maximum sequence length: 512 tokens
  • Training text data (raw): 995.49MB
  • Training text data (byte premium scaled): 1000.005MB
  • Training tokens: 231384576 (x10 epochs)
  • Vocabulary size: 50000
  • Compute cost: 1.180872235155456e+18 FLOPs or ~111.6 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 epo_latn_1000mb on huggingface.co

19
Total runs
0
24-hour runs
-1
3-day runs
-2
7-day runs
-3
30-day runs

More Information About epo_latn_1000mb huggingface.co Model

More epo_latn_1000mb license Visit here:

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

epo_latn_1000mb huggingface.co

epo_latn_1000mb huggingface.co is an AI model on huggingface.co that provides epo_latn_1000mb's model effect (), which can be used instantly with this goldfish-models epo_latn_1000mb model. huggingface.co supports a free trial of the epo_latn_1000mb model, and also provides paid use of the epo_latn_1000mb. Support call epo_latn_1000mb model through api, including Node.js, Python, http.

goldfish-models epo_latn_1000mb online free

epo_latn_1000mb huggingface.co is an online trial and call api platform, which integrates epo_latn_1000mb's modeling effects, including api services, and provides a free online trial of epo_latn_1000mb, you can try epo_latn_1000mb online for free by clicking the link below.

goldfish-models epo_latn_1000mb online free url in huggingface.co:

https://huggingface.co/goldfish-models/epo_latn_1000mb

epo_latn_1000mb install

epo_latn_1000mb is an open source model from GitHub that offers a free installation service, and any user can find epo_latn_1000mb on GitHub to install. At the same time, huggingface.co provides the effect of epo_latn_1000mb install, users can directly use epo_latn_1000mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

epo_latn_1000mb install url in huggingface.co:

https://huggingface.co/goldfish-models/epo_latn_1000mb

Url of epo_latn_1000mb

Provider of epo_latn_1000mb huggingface.co

goldfish-models
ORGANIZATIONS

Other API from goldfish-models