goldfish-models
/

mal_mlym_10mb

@@ -19,6 +19,8 @@ Goldfish is a suite of monolingual language models trained for 350 languages.
 This model is the <b>Malayalam</b> (Malayalam script) model trained on 10MB of data, after accounting for an estimated byte premium of 2.88; content-matched text in Malayalam takes on average 2.88x 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: mal_mlym 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 mlym).
 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).

 This model is the <b>Malayalam</b> (Malayalam script) model trained on 10MB of data, after accounting for an estimated byte premium of 2.88; content-matched text in Malayalam takes on average 2.88x 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: This language is available in Goldfish with other scripts (writing systems). See: mal_latn.
 Note: mal_mlym 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 mlym).
 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).