Goldfish is a suite of monolingual language models trained for 350 languages.
This model is the
Icelandic
(Latin script) model trained on 1000MB 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).
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): 1154.32MB
Training text data (byte premium scaled): 1000.005MB
Training tokens: 236872704 (x10 epochs)
Vocabulary size: 50000
Compute cost: 1.208963741515776e+18 FLOPs or ~114.3 NVIDIA A6000 GPU hours
Training datasets (percentages prior to deduplication):
@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_1000mb on huggingface.co
82
Total runs
0
24-hour runs
-15
3-day runs
-10
7-day runs
42
30-day runs
More Information About isl_latn_1000mb huggingface.co Model
isl_latn_1000mb huggingface.co is an AI model on huggingface.co that provides isl_latn_1000mb's model effect (), which can be used instantly with this goldfish-models isl_latn_1000mb model. huggingface.co supports a free trial of the isl_latn_1000mb model, and also provides paid use of the isl_latn_1000mb. Support call isl_latn_1000mb model through api, including Node.js, Python, http.
isl_latn_1000mb huggingface.co is an online trial and call api platform, which integrates isl_latn_1000mb's modeling effects, including api services, and provides a free online trial of isl_latn_1000mb, you can try isl_latn_1000mb online for free by clicking the link below.
goldfish-models isl_latn_1000mb online free url in huggingface.co:
isl_latn_1000mb is an open source model from GitHub that offers a free installation service, and any user can find isl_latn_1000mb on GitHub to install. At the same time, huggingface.co provides the effect of isl_latn_1000mb install, users can directly use isl_latn_1000mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.