goldfish-models / nor_latn_100mb

huggingface.co
Total runs: 39
24-hour runs: 0
7-day runs: 0
30-day runs: 31
Model's Last Updated: August 27 2024
text-generation

Introduction of nor_latn_100mb

Model Details of nor_latn_100mb

nor_latn_100mb

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the Norwegian (Latin script) model trained on 100MB of data, after accounting for an estimated byte premium of 1.13; content-matched text in Norwegian takes on average 1.13x 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: nor_latn is a macrolanguage code. Individual language codes nob_latn (Norwegian Bokmål) and nno_latn (Norwegian Nynorsk) are 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): 112.53MB
  • Training text data (byte premium scaled): 100.005MB
  • Training tokens: 25547264 (x10 epochs)
  • Vocabulary size: 50000
  • Compute cost: 1.30393607897088e+17 FLOPs or ~12.3 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 nor_latn_100mb on huggingface.co

39
Total runs
0
24-hour runs
1
3-day runs
0
7-day runs
31
30-day runs

More Information About nor_latn_100mb huggingface.co Model

More nor_latn_100mb license Visit here:

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

nor_latn_100mb huggingface.co

nor_latn_100mb huggingface.co is an AI model on huggingface.co that provides nor_latn_100mb's model effect (), which can be used instantly with this goldfish-models nor_latn_100mb model. huggingface.co supports a free trial of the nor_latn_100mb model, and also provides paid use of the nor_latn_100mb. Support call nor_latn_100mb model through api, including Node.js, Python, http.

goldfish-models nor_latn_100mb online free

nor_latn_100mb huggingface.co is an online trial and call api platform, which integrates nor_latn_100mb's modeling effects, including api services, and provides a free online trial of nor_latn_100mb, you can try nor_latn_100mb online for free by clicking the link below.

goldfish-models nor_latn_100mb online free url in huggingface.co:

https://huggingface.co/goldfish-models/nor_latn_100mb

nor_latn_100mb install

nor_latn_100mb is an open source model from GitHub that offers a free installation service, and any user can find nor_latn_100mb on GitHub to install. At the same time, huggingface.co provides the effect of nor_latn_100mb install, users can directly use nor_latn_100mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

nor_latn_100mb install url in huggingface.co:

https://huggingface.co/goldfish-models/nor_latn_100mb

Url of nor_latn_100mb

Provider of nor_latn_100mb huggingface.co

goldfish-models
ORGANIZATIONS

Other API from goldfish-models