#low-resource-languages

[ follow ]
#multilingual-models #progressive-training #modernbert #flashattention2 #kurdish-ocr
fromInfoQ
3 weeks ago

Hugging Face Introduces mmBERT, a Multilingual Encoder for 1,800+ Languages

Hugging Face has released mmBERT, a new multilingual encoder trained on more than 3 trillion tokens across 1,833 languages. The model builds on the ModernBERT architecture and is the first to significantly improve upon XLM-R, a long-time baseline for multilingual understanding tasks. mmBERT uses a progressive training schedule instead of training on all languages at once. It starts with 60 high-resource languages, expands to 110, and finally includes all 1,833 languages.
Artificial intelligence
Digital life
fromFortune Asia
3 months ago

The world's best AI models operate in English. Other languages-even major ones like Cantonese-risk falling further behind

AI translation models struggle with languages that have limited online data, leading to mistranslations and inaccuracies.
Scala
fromHackernoon
1 year ago

Why Lua Is the Ideal Benchmark for Testing Quantized Code Models | HackerNoon

Lua presents unique challenges for quantized model performance due to its low-resource status and unconventional programming paradigms.
[ Load more ]