Unable to download pretrain model.HTTP error 409

thanks for your delicate project.when I ran the evluate.py , it brake off at model-downloading stage. The error message was Traceback (most recent call last): File "/data/Graphormer/graphormer/evaluate/evaluate.py", line 130, in <module> main() File "/data/Graphormer/graphormer/evaluate/evaluate.py", line 120, in main eval(args, True, logger=logger) File "/data/Graphormer/graphormer/evaluate/evaluate.py", line 27, in eval model = task.build_model(cfg.model) File "/data/Graphormer/graphormer/tasks/graph_prediction.py", line 229, in build_model model = models.build_model(cfg, self) File "/data/fairseq/fairseq/models/__init__.py", line 105, in build_model return model.build_model(cfg, task) File "/data/Graphormer/graphormer/models/graphormer.py", line 149, in build_model return cls(args, encoder) File "/data/Graphormer/graphormer/models/graphormer.py", line 43, in __init__ self.load_state_dict(load_pretrained_model(args.pretrained_model_name)) File "/data/Graphormer/graphormer/pretrain/__init__.py", line 15, in load_pretrained_model return load_state_dict_from_url(PRETRAINED_MODEL_URLS[pretrained_model_name], progress=True)["model"] File "/opt/mamba/envs/graphormer/lib/python3.9/site-packages/torch/hub.py", line 571, in load_state_dict_from_url download_url_to_file(url, cached_file, hash_prefix, progress=progress) File "/opt/mamba/envs/graphormer/lib/python3.9/site-packages/torch/hub.py", line 437, in download_url_to_file u = urlopen(req) File "/opt/mamba/envs/graphormer/lib/python3.9/urllib/request.py", line 214, in urlopen return opener.open(url, data, timeout) File "/opt/mamba/envs/graphormer/lib/python3.9/urllib/request.py", line 523, in open response = meth(req, response) File "/opt/mamba/envs/graphormer/lib/python3.9/urllib/request.py", line 632, in http_response response = self.parent.error( File "/opt/mamba/envs/graphormer/lib/python3.9/urllib/request.py", line 561, in error return self._call_chain(*args) File "/opt/mamba/envs/graphormer/lib/python3.9/urllib/request.py", line 494, in _call_chain result = func(*args) File "/opt/mamba/envs/graphormer/lib/python3.9/urllib/request.py", line 641, in http_error_default raise HTTPError(req.full_url, code, msg, hdrs, fp) urllib.error.HTTPError: HTTP Error 409: Public access is not permitted on this storage account. (graphormer) root@bohrium-17396-1029993:/data/Graphormer/graphormer/evaluate# (graphormer) root@bohrium-17396-1029993:/data/Graphormer/graphormer/evaluate# vi /data/Graphormer/graphormer/pretrain/__init__.py (graphormer) root@bohrium-17396-1029993:/data/Graphormer/graphormer/evaluate# vi /data/Graphormer/graphormer/pretrain/__init__.py (graphormer) root@bohrium-17396-1029993:/data/Graphormer/graphormer/evaluate# wget https://ml2md.blob.core.windows.net/graphormer-ckpts/checkpoint_best_pcqm4mv1.pt --2023-07-21 15:07:36-- https://ml2md.blob.core.windows.net/graphormer-ckpts/checkpoint_best_pcqm4mv1.pt Resolving ml2md.blob.core.windows.net (ml2md.blob.core.windows.net)... 20.150.87.132 Connecting to ml2md.blob.core.windows.net (ml2md.blob.core.windows.net)|20.150.87.132|:443... connected. HTTP request sent, awaiting response... 409 Public access is not permitted on this storage account. 2023-07-21 15:07:37 ERROR 409: Public access is not permitted on this storage account..

When I download the model url https://ml2md.blob.core.windows.net/graphormer-ckpts/checkpoint_best_pcqm4mv1.pt manually using wget, it gave the same HTTP error.

My question is how could I fix the bug?

Start in graphormer/pretrain/init.py, especially load_pretrained_model and the PRETRAINED_MODEL_URLS entry used during graphormer/evaluate/evaluate.py. Check the configured checkpoint URL and run evaluate.py; done means the pretrained model downloads without HTTP 409 and evaluation proceeds past model loading.