Issues
- 3
同时测试多个子集的结果与单独测试每个子集的结果不同
#275 opened by xansar - 4
- 1
设置sample_num时,dataset的浅拷贝问题
#270 opened by xansar - 1
vllm_vllm_gpu_memory_utilization参数无效
#271 opened by xansar - 4
Support fine-tuning LLaMA3?
#264 opened by cnlinxi - 1
eval log格式问题
#258 opened by xansar - 2
Cannot load C-Eval from local directory
#220 opened by xansar - 1
- 2
Index out of bounds error when evaluating Mistral-7b-instruct-v0.2 on some instances of MMLU
#217 opened by ShadowTinker