QwenLM / Qwen2.5-Coder

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.
2.94k stars 192 forks source link

Error in evaluation on Qwen2.5-Coder #172

Closed Zephyreeze closed 2 days ago

Zephyreeze commented 2 days ago

When run 'bash run_evaluate_cq2.5.sh' to evaluate HumanEval and MBPP, there is an error this line:"from evalplus.data import get_human_eval_plus"(line24 in generation.py). It seems that "data" does not exist in evalplus?

cyente commented 2 days ago

Please provide us with more detailed information, including the log and the environment.

Zephyreeze commented 2 days ago

Thanks for your reply! I have settled this question. I just need to pip install evalplus...