๊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
159 ํŒ”๋กœ์ž‰ ์ค‘    12K ํŒฌ
SkyJM-Gen-9B is now live on ModelScope! A 9B visual reward model for text-to-image generation that ranks candidate images with prompt-conditioned rubrics, not a single flat score.๐Ÿš€ ๐Ÿค– ๐Ÿ† Text-to-image judging: tops listed reward models on MMRB2, GenAI-Bench, and GenAI-Bench-Verified, with 72.0 / 74.1 / 84.5 ๐Ÿงฉ RubricRM workflow: generates evaluation dimensions, weights, and scoring descriptors for each prompt, then scores both candidate images by dimension โš™๏ธ Training recipe: rubric-trajectory SFT + dimension-level GRPO for more structured preference judgment Apache 2.0. vLLM and Transformers ready.
๋” ๋ณด๊ธฐ