goldfish-models / zho_hans_10mb

huggingface.co
Total runs: 45
24-hour runs: 0
7-day runs: 7
30-day runs: 17
Model's Last Updated: August 27 2024
text-generation

Introduction of zho_hans_10mb

Model Details of zho_hans_10mb

zho_hans_10mb

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the Chinese (Han Simplified script) model trained on 10MB of data, after accounting for an estimated byte premium of 0.94; content-matched text in Chinese takes on average 0.94x 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: zho_hans is a macrolanguage code. None of its contained individual languages are included in Goldfish (for script hans).

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: 39087104
  • Maximum sequence length: 512 tokens
  • Training text data (raw): 9.36MB
  • Training text data (byte premium scaled): 10.005MB
  • Training tokens: 2137088 (x10 epochs)
  • Vocabulary size: 50000
  • Compute cost: 1616140314869760.0 FLOPs or ~0.2 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 zho_hans_10mb on huggingface.co

45
Total runs
0
24-hour runs
1
3-day runs
7
7-day runs
17
30-day runs

More Information About zho_hans_10mb huggingface.co Model

More zho_hans_10mb license Visit here:

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

zho_hans_10mb huggingface.co

zho_hans_10mb huggingface.co is an AI model on huggingface.co that provides zho_hans_10mb's model effect (), which can be used instantly with this goldfish-models zho_hans_10mb model. huggingface.co supports a free trial of the zho_hans_10mb model, and also provides paid use of the zho_hans_10mb. Support call zho_hans_10mb model through api, including Node.js, Python, http.

goldfish-models zho_hans_10mb online free

zho_hans_10mb huggingface.co is an online trial and call api platform, which integrates zho_hans_10mb's modeling effects, including api services, and provides a free online trial of zho_hans_10mb, you can try zho_hans_10mb online for free by clicking the link below.

goldfish-models zho_hans_10mb online free url in huggingface.co:

https://huggingface.co/goldfish-models/zho_hans_10mb

zho_hans_10mb install

zho_hans_10mb is an open source model from GitHub that offers a free installation service, and any user can find zho_hans_10mb on GitHub to install. At the same time, huggingface.co provides the effect of zho_hans_10mb install, users can directly use zho_hans_10mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

zho_hans_10mb install url in huggingface.co:

https://huggingface.co/goldfish-models/zho_hans_10mb

Url of zho_hans_10mb

Provider of zho_hans_10mb huggingface.co

goldfish-models
ORGANIZATIONS

Other API from goldfish-models