CUHK-ARISE/EmotionBench

LLama Evaluation

cosmoquester opened this issue · 1 comments

It seems that this codes doesn't support LLama although llama was evaluated in the paper.
How can I evaluate LLaMa models?

Sorry for my late reply. You can refer to the Benchmarking Your Own Model section in the README to write code to test LLaMA models.

We will push the code for evaluating LLaMA soon.