jbdel / vilmedic

ViLMedic (Vision-and-Language medical research) is a modular framework for vision and language multimodal research in the medical field
MIT License
151 stars 20 forks source link

Unable to download and access models zoo #25

Open fbrynpk opened 1 month ago

fbrynpk commented 1 month ago

Hi, thank you for the code and an amazing work to access some of the pre-trained model, but when I tried to run the code, I was unable to download the model from the models zoo and end up with an empty folder, could you help me understand as to why this happened and maybe help fix this? I tried to run the code according to the Vilmedic website quick start guide!

Downloading in C:\Users\User\AppData\Local\vilmedic\vilmedic\Cache\zoo\models Retrieving folder list Traceback (most recent call last): File "c:/Users/User/Desktop/vilmedic/convirt.py", line 2, in model, processor = AutoModel.from_pretrained("rrg/biomed-roberta-baseline-mimic") File "C:\Users\User\anaconda3\envs\vilmedic\lib\site-packages\vilmedic\zoo\modeling_auto.py", line 69, in from_pretrained assert len(checkpoint) == 1, "More than one or no checkpoint found" AssertionError: More than one or no checkpoint found