Commit
•
4690c8d
1
Parent(s):
905fb25
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -22,6 +22,8 @@ Goldfish is a suite of monolingual language models trained for 350 languages.
|
|
| 22 |
This model is the <b>Goan Konkani</b> (Devanagari script) model trained on 10MB of data, after accounting for an estimated byte premium of 1.74; content-matched text in Goan Konkani takes on average 1.74x as many UTF-8 bytes to encode as English.
|
| 23 |
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).
|
| 24 |
|
|
|
|
|
|
|
| 25 |
Note: gom_deva is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. It is not contained in any macrolanguage codes contained in Goldfish (for script deva).
|
| 26 |
|
| 27 |
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).
|
|
|
|
| 22 |
This model is the <b>Goan Konkani</b> (Devanagari script) model trained on 10MB of data, after accounting for an estimated byte premium of 1.74; content-matched text in Goan Konkani takes on average 1.74x as many UTF-8 bytes to encode as English.
|
| 23 |
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).
|
| 24 |
|
| 25 |
+
Note: This language is available in Goldfish with other scripts (writing systems). See: gom_latn.
|
| 26 |
+
|
| 27 |
Note: gom_deva is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. It is not contained in any macrolanguage codes contained in Goldfish (for script deva).
|
| 28 |
|
| 29 |
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).
|