Goldfish is a suite of monolingual language models trained for 350 languages.
This model is the
Chinese
(Han Simplified script) model trained on 1000MB of data, after accounting for an estimated byte premium of 0.94; content-matched text in Chinese takes on average 0.94x 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: zho_hans is a
macrolanguage
code. None of its contained individual languages are included in Goldfish (for script hans).
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): 935.97MB
Training text data (byte premium scaled): 1000.005MB
Training tokens: 206204416 (x10 epochs)
Vocabulary size: 50000
Compute cost: 1.052469149958144e+18 FLOPs or ~99.5 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 zho_hans_1000mb on huggingface.co
248
Total runs
0
24-hour runs
8
3-day runs
40
7-day runs
219
30-day runs
More Information About zho_hans_1000mb huggingface.co Model
zho_hans_1000mb huggingface.co is an AI model on huggingface.co that provides zho_hans_1000mb's model effect (), which can be used instantly with this goldfish-models zho_hans_1000mb model. huggingface.co supports a free trial of the zho_hans_1000mb model, and also provides paid use of the zho_hans_1000mb. Support call zho_hans_1000mb model through api, including Node.js, Python, http.
zho_hans_1000mb huggingface.co is an online trial and call api platform, which integrates zho_hans_1000mb's modeling effects, including api services, and provides a free online trial of zho_hans_1000mb, you can try zho_hans_1000mb online for free by clicking the link below.
goldfish-models zho_hans_1000mb online free url in huggingface.co:
zho_hans_1000mb is an open source model from GitHub that offers a free installation service, and any user can find zho_hans_1000mb on GitHub to install. At the same time, huggingface.co provides the effect of zho_hans_1000mb install, users can directly use zho_hans_1000mb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.