Problem with import timm for using it

I tried to load a model using the interface provided in timm by

import timm
model = timm.create_model(‘model_name’, pretrained=True)

but got

[libprotobuf FATAL google/protobuf/stubs/common.cc:87] This program was compiled against version 3.9.2 of the Protocol Buffer runtime library, which is not compatible with the installed version (3.18.0). Contact the program author for an update. If you compiled the program yourself, make sure that your headers are from the same version of Protocol Buffers as your link-time library. (Version verification failed in “bazel-out/k8-opt/bin/tensorflow/core/framework/tensor_shape.pb.cc”.)
terminate called after throwing an instance of ‘google::protobuf::FatalException’
what(): This program was compiled against version 3.9.2 of the Protocol Buffer runtime library, which is not compatible with the installed version (3.18.0). Contact the program author for an update. If you compiled the program yourself, make sure that your headers are from the same version of Protocol Buffers as your link-time library. (Version verification failed in “bazel-out/k8-opt/bin/tensorflow/core/framework/tensor_shape.pb.cc”.)
Aborted (core dumped)

Are you mixing TF/PyTorch together, as this error seems to be raised by TF?

Version verification failed in “bazel-out/k8-opt/bin/tensorflow/core/framework/tensor_shape.pb.cc”

Based on the warning it seems that just no pretrained weights exist for this model and I think you would need to train it from scratch (or check if updating timm might ship with new pretrained weights).