Chai-1报错：Can‘t load tokenizer for ‘facebook/esm2_t36_3B_UR50D‘

在使用Chai-1时报错：

OSError: Can't load tokenizer for 'facebook/esm2_t36_3B_UR50D'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'facebook/esm2_t36_3B_UR50D' is the correct path to a directory containing all relevant files for a EsmTokenizer tokenizer.

解决方案：
去 https://huggingface.co/facebook/esm2_t36_3B_UR50D/tree/main 将所有的文件下载下来。
放到某个 facebook/esm2_t36_3B_UR50D的目录下。
我放到了

~/anaconda3/envs/Chai-1/lib/python3.10/site-packages/chai_lab/data/dataset/embeddings/

ps：创建了一个环境名为Chai-1，python=3.10

然后在~/anaconda3/envs/Chai-1/lib/python3.10/site-packages/chai_lab/data/dataset/embeddings/目录下的esm.py中搜索esm2_t36_3B_UR50D，将其路径改为绝对路径。

即可正常使用Chai-1预测复合物。