(py3.8) 202312150037@ubuntu:/data/zht/learn_pytorch/CogView2-main$ ./text2image.sh --input-source input.txt
[2024-04-03 09:01:21,408] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Please install apex to use fused_layer_norm, fall back to torch.nn.LayerNorm
WARNING: No training data specified
using world size: 1 and model-parallel size: 1
initializing model parallel with size 1
Traceback (most recent call last):
File "cogview2_text2image.py", line 233, in
main(args)
File "cogview2_text2image.py", line 48, in main
model, args = InferenceModel.from_pretrained(args, 'coglm')
File "/home/202312150037/anaconda3/envs/py3.8/lib/python3.8/site-packages/SwissArmyTransformer/model/base_model.py", line 152, in from_pretrained
model_path = auto_create(name, path=home_path, url=url)
File "/home/202312150037/anaconda3/envs/py3.8/lib/python3.8/site-packages/SwissArmyTransformer/resources/download.py", line 36, in auto_create
os.makedirs(os.path.dirname(file_path), exist_ok=True)
File "/home/202312150037/anaconda3/envs/py3.8/lib/python3.8/os.py", line 213, in makedirs
makedirs(head, exist_ok=exist_ok)
File "/home/202312150037/anaconda3/envs/py3.8/lib/python3.8/os.py", line 223, in makedirs
mkdir(name, mode)
PermissionError: [Errno 13] Permission denied: '/sharefs'
(py3.8) 202312150037@ubuntu:/data/zht/learn_pytorch/CogView2-main$ ./text2image.sh --input-source input.txt
[2024-04-03 09:01:21,408] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Please install apex to use fused_layer_norm, fall back to torch.nn.LayerNorm
WARNING: No training data specified
using world size: 1 and model-parallel size: 1