goldfish-models / kac_latn_5mb

huggingface.co
Total runs: 196
24-hour runs: 0
7-day runs: 42
30-day runs: 168
Model's Last Updated: August 27 2024
text-generation

Introduction of kac_latn_5mb

Model Details of kac_latn_5mb

kac_latn_5mb

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the Kachin (Latin script) model trained on 5MB of data, after accounting for an estimated byte premium of 1.35; content-matched text in Kachin takes on average 1.35x 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: kac_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: 27552768
  • Maximum sequence length: 512 tokens
  • Training text data (raw): 6.73MB
  • Training text data (byte premium scaled): 5.005MB
  • Training tokens: 1790976 (x10 epochs)
  • Vocabulary size: 26984
  • Compute cost: 1354415304867840.0 FLOPs or ~0.1 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 kac_latn_5mb on huggingface.co

196
Total runs
0
24-hour runs
1
3-day runs
42
7-day runs
168
30-day runs

More Information About kac_latn_5mb huggingface.co Model

More kac_latn_5mb license Visit here:

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

kac_latn_5mb huggingface.co

kac_latn_5mb huggingface.co is an AI model on huggingface.co that provides kac_latn_5mb's model effect (), which can be used instantly with this goldfish-models kac_latn_5mb model. huggingface.co supports a free trial of the kac_latn_5mb model, and also provides paid use of the kac_latn_5mb. Support call kac_latn_5mb model through api, including Node.js, Python, http.

goldfish-models kac_latn_5mb online free

kac_latn_5mb huggingface.co is an online trial and call api platform, which integrates kac_latn_5mb's modeling effects, including api services, and provides a free online trial of kac_latn_5mb, you can try kac_latn_5mb online for free by clicking the link below.

goldfish-models kac_latn_5mb online free url in huggingface.co:

https://huggingface.co/goldfish-models/kac_latn_5mb

kac_latn_5mb install

kac_latn_5mb is an open source model from GitHub that offers a free installation service, and any user can find kac_latn_5mb on GitHub to install. At the same time, huggingface.co provides the effect of kac_latn_5mb install, users can directly use kac_latn_5mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

kac_latn_5mb install url in huggingface.co:

https://huggingface.co/goldfish-models/kac_latn_5mb

Url of kac_latn_5mb

Provider of kac_latn_5mb huggingface.co

goldfish-models
ORGANIZATIONS

Other API from goldfish-models