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

Maziyar PANAHI
@MaziyarPanahi
the on-device clinical AI guy | building @OpenMed_AI | making open models @arcee_ai | AI infra & research @CNRS | follow for local clinical AI demos
๊ฐ€์ž… October 2010
344 ํŒ”๋กœ์ž‰ ์ค‘    19.7K ํŒฌ
i'm releasing 180,000 Jev-format tool-calling decisions, typed and labeled, so a tiny model can make them instead of your LLM ๐Ÿ”ฅ which tool, whether to call one, are the args complete. clean splits. built on NVIDIA's open agent data. train your own router on it, then race Jev.
๋” ๋ณด๊ธฐ