AI Jun

Results 6 comments of AI Jun

Hi, yes, I will update soon. I am a lit busy recently. ------------------ 原始邮件 ------------------ 发件人: "Keyird/DeepLearning-TensorFlow2.0"

请问一下,judge model的选择对测试集指标的影响大吗?

> Hi, [@lyzhongcrd](https://github.com/lyzhongcrd) , Yeah. However, we recommend you use the same LLM as the judger for all LMMs to make it comparable. For MCQ or Y/N benchmarks, when LLMs...