Goldfish is a suite of monolingual language models trained for 350 languages.
This model is the
Scottish Gaelic
(Latin script) model trained on 5MB of data, after accounting for an estimated byte premium of 0.99; content-matched text in Scottish Gaelic takes on average 0.99x 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: gla_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: 35941376
Maximum sequence length: 512 tokens
Training text data (raw): 4.97MB
Training text data (byte premium scaled): 5.005MB
Training tokens: 1152000 (x10 epochs)
Vocabulary size: 44264
Compute cost: 870944593674240.0 FLOPs or ~0.1 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 gla_latn_5mb on huggingface.co
211
Total runs
0
24-hour runs
42
3-day runs
52
7-day runs
194
30-day runs
More Information About gla_latn_5mb huggingface.co Model
gla_latn_5mb huggingface.co is an AI model on huggingface.co that provides gla_latn_5mb's model effect (), which can be used instantly with this goldfish-models gla_latn_5mb model. huggingface.co supports a free trial of the gla_latn_5mb model, and also provides paid use of the gla_latn_5mb. Support call gla_latn_5mb model through api, including Node.js, Python, http.
gla_latn_5mb huggingface.co is an online trial and call api platform, which integrates gla_latn_5mb's modeling effects, including api services, and provides a free online trial of gla_latn_5mb, you can try gla_latn_5mb online for free by clicking the link below.
goldfish-models gla_latn_5mb online free url in huggingface.co:
gla_latn_5mb is an open source model from GitHub that offers a free installation service, and any user can find gla_latn_5mb on GitHub to install. At the same time, huggingface.co provides the effect of gla_latn_5mb install, users can directly use gla_latn_5mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.