Goldfish is a suite of monolingual language models trained for 350 languages.
This model is the
Lithuanian
(Latin script) model trained on 100MB of data, after accounting for an estimated byte premium of 1.03; content-matched text in Lithuanian takes on average 1.03x 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: lit_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): 103.00MB
Training text data (byte premium scaled): 100.005MB
Training tokens: 20116480 (x10 epochs)
Vocabulary size: 50000
Compute cost: 1.02646484434944e+17 FLOPs or ~9.7 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 lit_latn_100mb on huggingface.co
30
Total runs
0
24-hour runs
-4
3-day runs
-3
7-day runs
14
30-day runs
More Information About lit_latn_100mb huggingface.co Model
lit_latn_100mb huggingface.co is an AI model on huggingface.co that provides lit_latn_100mb's model effect (), which can be used instantly with this goldfish-models lit_latn_100mb model. huggingface.co supports a free trial of the lit_latn_100mb model, and also provides paid use of the lit_latn_100mb. Support call lit_latn_100mb model through api, including Node.js, Python, http.
lit_latn_100mb huggingface.co is an online trial and call api platform, which integrates lit_latn_100mb's modeling effects, including api services, and provides a free online trial of lit_latn_100mb, you can try lit_latn_100mb online for free by clicking the link below.
goldfish-models lit_latn_100mb online free url in huggingface.co:
lit_latn_100mb is an open source model from GitHub that offers a free installation service, and any user can find lit_latn_100mb on GitHub to install. At the same time, huggingface.co provides the effect of lit_latn_100mb install, users can directly use lit_latn_100mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.