Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -2,8 +2,8 @@
|
|
| 2 |
---
|
| 3 |
license: apache-2.0
|
| 4 |
language:
|
| 5 |
-
- arb
|
| 6 |
- ara
|
|
|
|
| 7 |
datasets:
|
| 8 |
- oscar-corpus/OSCAR-2109
|
| 9 |
library_name: transformers
|
|
@@ -19,7 +19,7 @@ Goldfish is a suite of monolingual language models trained for 350 languages.
|
|
| 19 |
This model is the <b>Standard Arabic</b> (Arabic script) model trained on 5MB of data, after accounting for an estimated byte premium of 1.47; content-matched text in Standard Arabic takes on average 1.47x as many UTF-8 bytes to encode as English.
|
| 20 |
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).
|
| 21 |
|
| 22 |
-
Note: arb_arab is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code.
|
| 23 |
|
| 24 |
All training and hyperparameter details are in our paper, [Goldfish: Monolingual Language Models for 350 Languages (Chang et al., 2024)](https://github.com/tylerachang/goldfish/blob/main/goldfish_paper_20240815.pdf).
|
| 25 |
|
|
|
|
| 2 |
---
|
| 3 |
license: apache-2.0
|
| 4 |
language:
|
|
|
|
| 5 |
- ara
|
| 6 |
+
- arb
|
| 7 |
datasets:
|
| 8 |
- oscar-corpus/OSCAR-2109
|
| 9 |
library_name: transformers
|
|
|
|
| 19 |
This model is the <b>Standard Arabic</b> (Arabic script) model trained on 5MB of data, after accounting for an estimated byte premium of 1.47; content-matched text in Standard Arabic takes on average 1.47x as many UTF-8 bytes to encode as English.
|
| 20 |
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).
|
| 21 |
|
| 22 |
+
Note: arb_arab is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. However, this model may also be useful for other Arabic dialects with less data.
|
| 23 |
|
| 24 |
All training and hyperparameter details are in our paper, [Goldfish: Monolingual Language Models for 350 Languages (Chang et al., 2024)](https://github.com/tylerachang/goldfish/blob/main/goldfish_paper_20240815.pdf).
|
| 25 |
|