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

Ant Ling
@AntLingAGI
MoE model series with foundation (Ling), reasoning (Ring) and any-to-any (Ming) from Ant Groupโ€™s AGI initiative, @TheInclusionAI.
๊ฐ€์ž… April 2025
5 ํŒ”๋กœ์ž‰ ์ค‘    12.8K ํŒฌ
Today, weโ€™re releasing the open weights for Ling-3.0-flash. ๐ŸŽ‰ Official BF16 and FP8-quantized versions are now available, so you can choose the option that best fits your hardware, performance requirements, and deployment needs.
๋” ๋ณด๊ธฐ