3 stories, newest first · one card per story
Tiny Aya L2-Thinker, a 3.35B model, achieves over 93 percent in-language reasoning across 60 languages via optimized multilingual data mixing; weights released.
Researchers train Tiny Aya L2-Thinker, a 3.35B model achieving over 93% in-language reasoning across 60 languages via multilingual data mixing.
Controlled mid-training experiments on Qwen3-8B-Base find each domain has a 10-40% coverage optimum and domain gaps survive alignment SFT.
Today 1.6K readers · 2.4K views · 775 reads · all time 189K views