各种量化版本的模型，在不同测评数据集上面的表现怎么样，有没有具体的测试结果
#29
by
huanfa
- opened
测评数据集包括C-Eval、MMLU、TriviaQA、GSM8K等数据集
Hi what is your question? :)
Hi what is your question? :)
My question is: How do various quantitative versions of models perform on different evaluation datasets, and are there specific test results