SuperAPI AI Directory

All AI tools

35,738 results · Page 303 of 993

MiLM-6B

AI developer platforms

MiLM-6B is a large-scale pretrained language model developed by Xiaomi, with a parameter scale of 6.4 billion. Official information states that it achieves the best results among models of the same size on both C-Eval and CMMLU, two Chinese evaluation benchmarks. C-Eval is a Chinese foundation model evaluation dataset covering 52 disciplines and four difficulty levels; CMMLU is a Chinese evaluation benchmark covering 67 topics, used to evaluate language models' knowledge and reasoning abilities in Chinese contexts. The model is provided as an open-source repository on GitHub, and the repository address is https://github.com/XiaoMi/MiLM-6B 。

Read more