fast-thinking

Tag

Cards List
#fast-thinking

Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild

arXiv cs.CL · 2026-05-22 Cached

Hy-MT2 is a family of fast, efficient multilingual translation models from Tencent, available in 1.8B, 7B, and 30B-A3B sizes, supporting 33 languages and outperforming previous open-source and commercial models.

0 favorites 0 likes
#fast-thinking

tencent/Hy-MT2-7B

Hugging Face Models Trending · 2026-05-11 Cached

Tencent open-sourced the Hy-MT2 family of fast-thinking multilingual translation models (1.8B, 7B, 30B-A3B) supporting 33 languages, along with extreme quantization for on-device deployment and a new instruction-following benchmark IFMTBench.

0 favorites 0 likes
← Back to home

Submit Feedback