AaronWhy / LLM_Evaluation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

LLM_Evaluation

mmlu_model_eval_multi_choice.ipynb: Evaluate model with multiple choice style. mmlu_model_eval_cloze_prompt.ipynb: Evaluate model with probabilities of sentences.

About


Languages

Language:Jupyter Notebook 100.0%