goldfish-models commited on
Commit
5384117
1 Parent(s): faed5ef

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -19,6 +19,8 @@ Goldfish is a suite of monolingual language models trained for 350 languages.
19
  This model is the <b>Northern Uzbek</b> (Cyrillic script) model trained on 208MB of data (all our data in the language), after accounting for an estimated byte premium of 2.01; content-matched text in Northern Uzbek takes on average 2.01x 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: uzn_cyrl is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. Macrolanguage code uzb_cyrl (Uzbek) is included in Goldfish. Consider using that model depending on your use case.
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).
 
19
  This model is the <b>Northern Uzbek</b> (Cyrillic script) model trained on 208MB of data (all our data in the language), after accounting for an estimated byte premium of 2.01; content-matched text in Northern Uzbek takes on average 2.01x 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: This language is available in Goldfish with other scripts (writing systems). See: uzn_latn.
23
+
24
  Note: uzn_cyrl is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. Macrolanguage code uzb_cyrl (Uzbek) is included in Goldfish. Consider using that model depending on your use case.
25
 
26
  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).