goldfish-models / isl_latn_10mb

huggingface.co
Total runs: 40
24-hour runs: 0
7-day runs: -1
30-day runs: 23
Model's Last Updated: August 27 2024
text-generation

Introduction of isl_latn_10mb

Model Details of isl_latn_10mb

isl_latn_10mb

Goldfish is a suite of monolingual language models trained for 350 languages. This model is the Icelandic (Latin script) model trained on 10MB of data, after accounting for an estimated byte premium of 1.15; content-matched text in Icelandic takes on average 1.15x 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: isl_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: 39087104
  • Maximum sequence length: 512 tokens
  • Training text data (raw): 11.55MB
  • Training text data (byte premium scaled): 10.005MB
  • Training tokens: 2450944 (x10 epochs)
  • Vocabulary size: 50000
  • Compute cost: 1852490860462080.0 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 isl_latn_10mb on huggingface.co

40
Total runs
0
24-hour runs
0
3-day runs
-1
7-day runs
23
30-day runs

More Information About isl_latn_10mb huggingface.co Model

More isl_latn_10mb license Visit here:

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

isl_latn_10mb huggingface.co

isl_latn_10mb huggingface.co is an AI model on huggingface.co that provides isl_latn_10mb's model effect (), which can be used instantly with this goldfish-models isl_latn_10mb model. huggingface.co supports a free trial of the isl_latn_10mb model, and also provides paid use of the isl_latn_10mb. Support call isl_latn_10mb model through api, including Node.js, Python, http.

goldfish-models isl_latn_10mb online free

isl_latn_10mb huggingface.co is an online trial and call api platform, which integrates isl_latn_10mb's modeling effects, including api services, and provides a free online trial of isl_latn_10mb, you can try isl_latn_10mb online for free by clicking the link below.

goldfish-models isl_latn_10mb online free url in huggingface.co:

https://huggingface.co/goldfish-models/isl_latn_10mb

isl_latn_10mb install

isl_latn_10mb is an open source model from GitHub that offers a free installation service, and any user can find isl_latn_10mb on GitHub to install. At the same time, huggingface.co provides the effect of isl_latn_10mb install, users can directly use isl_latn_10mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

isl_latn_10mb install url in huggingface.co:

https://huggingface.co/goldfish-models/isl_latn_10mb

Url of isl_latn_10mb

Provider of isl_latn_10mb huggingface.co

goldfish-models
ORGANIZATIONS

Other API from goldfish-models