Goldfish is a suite of monolingual language models trained for 350 languages.
This model is the
Afrikaans
(Latin script) model trained on 1000MB of data, after accounting for an estimated byte premium of 1.04; content-matched text in Afrikaans takes on average 1.04x 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: afr_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): 1037.23MB
Training text data (byte premium scaled): 1000.005MB
Training tokens: 239682048 (x10 epochs)
Vocabulary size: 50000
Compute cost: 1.22326738993152e+18 FLOPs or ~115.7 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 afr_latn_1000mb on huggingface.co
30
Total runs
0
24-hour runs
0
3-day runs
5
7-day runs
10
30-day runs
More Information About afr_latn_1000mb huggingface.co Model
afr_latn_1000mb huggingface.co is an AI model on huggingface.co that provides afr_latn_1000mb's model effect (), which can be used instantly with this goldfish-models afr_latn_1000mb model. huggingface.co supports a free trial of the afr_latn_1000mb model, and also provides paid use of the afr_latn_1000mb. Support call afr_latn_1000mb model through api, including Node.js, Python, http.
afr_latn_1000mb huggingface.co is an online trial and call api platform, which integrates afr_latn_1000mb's modeling effects, including api services, and provides a free online trial of afr_latn_1000mb, you can try afr_latn_1000mb online for free by clicking the link below.
goldfish-models afr_latn_1000mb online free url in huggingface.co:
afr_latn_1000mb is an open source model from GitHub that offers a free installation service, and any user can find afr_latn_1000mb on GitHub to install. At the same time, huggingface.co provides the effect of afr_latn_1000mb install, users can directly use afr_latn_1000mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.