๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Tencent Hy
@TencentHunyuan
Tencent's foundation model for text, image, video, and 3D generation.
๊ฐ€์ž… July 2024
8 ํŒ”๋กœ์ž‰ ์ค‘    46.5K ํŒฌ
We're open-sourcing Hy-MT1.5-1.8B-1.25bit โ€” a 440MB translation model that runs fully offline on your phone, supports 33 languages, and outperforms Google Translate. At 1.8B parameters, it matches commercial translation APIs and 235B-scale models on standard benchmarks. By quantizing to 1.25-bit, memory drops from 3.3GB (FP16) to 440MB โ€” 25% smaller and ~10% faster than prior 1.67-bit approaches, with no accuracy loss. Covers 33 languages, 5 dialects, and 1,056 translation directions including minority languages like Tibetan and Mongolian. Our translation model has won 30 first-place rankings in international MT competitions and is already deployed across multiple Tencent products.๐Ÿ† ๐Ÿ“ฒDemo APK (Android): ๐Ÿค—Hugging Face:: ๐Ÿ”—GitHub: ๐Ÿ“„Paper:
๋” ๋ณด๊ธฐ