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

ModelScope
@ModelScope2022
Driving innovations with open communities. ๐Ÿ’ฌ Join our Discord:
๊ฐ€์ž… April 2024
198 ํŒ”๋กœ์ž‰ ์ค‘    16.8K ํŒฌ
NeoHorse-Jev-4B is now openโ€”a compact model built to turn application states directly into structured decisions and probabilities. ๐Ÿค– ๐Ÿ† Scores 77.70 across six text decision benchmark groups, ranking first among the four open-weight models with complete results in the comparison. โšก Prefill-only inference avoids autoregressive answer generation and supports three decision primitives: Choice for action selection, Noul for yes/no judgment, and Score for ordered ratings. ๐ŸŽฎ The same interface can power request routing, tool selection, workflow control, games, robot manipulation, and autonomous-driving simulations. ๐Ÿ–ผ๏ธ Supports text inputs or a single image combined with text, returning normalized probabilities that applications can use directly. ๐Ÿ› ๏ธ Deploy locally through vLLM, SGLang, Python, CLI, or HTTP. Apache 2.0.
๋” ๋ณด๊ธฐ