GPT-4/ChatGPT Evaluation Code

tianyi-lab / Cherry_LLM

[NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other models

287 stars 19 forks source link

GPT-4/ChatGPT Evaluation Code #9

Closed mshen2 closed 10 months ago

mshen2 commented 10 months ago

Hi authors. I am just wondering if it is possible to share the eval_after_wrap.py code. Thanks!

MingLiiii commented 10 months ago

I am sorry for the late reply and for the typo! The "eval_after_wrap.py" is the "evaluation/generation/eval.py" code. You can directly modify the .sh scripts by replacing "eval_after_wrap.py" with "evaluation/generation/eval.py".