duguodong

Could you please share the method how to train the multi-view model ? It seems that there is no trainer for multi-view version.

hello, 我想咨询一下在MT-bench上测试时，使用的reference answer 是通过 gen_api_answer.py --model gpt-4-0125-preview这个命令来获取的吗？ 生成的reference answer有80个，然后把其中100～130个用official comment[https://github.com/lm-sys/FastChat/pull/3158](url)这里的正确的30个进行替换吗？ 总结一下；judge model 是用gpt-4-0125-preview， 但是80个问题的reference answer 是怎么获取呢，judge的结果是可复现的还是会有波动呢？