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

Nanbeige
@nanbeige
Nanbeige LLM Lab, BOSS Zhipin (Kanzhun Limited)
๊ฐ€์ž… December 2023
310 ํŒ”๋กœ์ž‰ ์ค‘    2.7K ํŒฌ
With the release of OpenAI's GPT-6 Astra @openai and @rasbt's widely shared article, Nanbeige4.2-3B ( is back in the spotlight! ๐Ÿš€ Built on a Looped Transformer, our 3B model consistently outperforms larger models (e.g., Qwen3.5-9B, Gemma4-12B) across key Agent benchmarks: SWE-Bench Pro, Terminal-Bench, GDPval, and more. Nanbeige4.5 is currently training with LoopSplit, mHC + depth attention, and concatenated n-gram embeddings. Stay tuned!
๋” ๋ณด๊ธฐ