Distributed training is the only way to go.

[xuboot]

The following values were not passed to accelerate launch and had defaults used instead: --num_processes was set to a value of 1 --num_machines was set to a value of 1 --mixed_precision was set to a value of 'no' --dynamo_backend was set to a value of 'no' To avoid this warning pass in values for each of the problematic parameters or run accelerate config. /usr/local/data/miniconda3/envs/vct/lib/python3.8/site-packages/accelerate/accelerator.py:321: UserWarning: log_with=tensorboard was passed but no supported trackers are currently installed. warnings.warn(f"log_with={log_with} was passed but no supported trackers are currently installed.") 08/28/2023 13:59:19 - INFO - main - Distributed environment: NO Num processes: 1 Process index: 0 Local process index: 0 Device: cuda Mixed precision type: no

Traceback (most recent call last): File "main.py", line 829, in args = multi_concept_inversion() File "main.py", line 551, in multi_concept_inversion tokenizer = MultiTokenCLIPTokenizer.from_pretrained(args.pretrained_model_name_or_path, subfolder="tokenizer") File "/usr/local/data/miniconda3/envs/vct/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 1763, in from_pretrained resolved_vocab_files[file_id] = cached_file( File "/usr/local/data/miniconda3/envs/vct/lib/python3.8/site-packages/transformers/utils/hub.py", line 409, in cached_file resolved_file = hf_hub_download( File "/usr/local/data/miniconda3/envs/vct/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 110, in _inner_fn validate_repo_id(arg_value) File "/usr/local/data/miniconda3/envs/vct/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 158, in validate_repo_id raise HFValidationError( huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/put/your/downloaded/huggingface/model'. Use repo_type argument if needed. Traceback (most recent call last): File "/usr/local/data/miniconda3/envs/vct/bin/accelerate", line 8, in sys.exit(main()) File "/usr/local/data/miniconda3/envs/vct/lib/python3.8/site-packages/accelerate/commands/accelerate_cli.py", line 45, in main args.func(args) File "/usr/local/data/miniconda3/envs/vct/lib/python3.8/site-packages/accelerate/commands/launch.py", line 1104, in launch_command simple_launcher(args) File "/usr/local/data/miniconda3/envs/vct/lib/python3.8/site-packages/accelerate/commands/launch.py", line 567, in simple_launcher raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) subprocess.CalledProcessError: Command '['/usr/local/data/miniconda3/envs/vct/bin/python', 'main.py', '--concept_image_dir=./examples/concept_image', '--content_image_dir=./examples/content_image', '--pretrained_model_name_or_path=/put/your/downloaded/huggingface/model', '--output_image_path=./outputs', '--initializer_token=girl', '--max_train_steps=50', '--concept_embedding_num=3', '--cross_attention_injection_ratio=0.2', '--self_attention_injection_ratio=0.9', '--use_l1']' returned non-zero exit status 1.

[CrystalNeuro]

I think this error is caused by the absence of the "pretrained_model_name_or_path" argument.

[gustn9609]

@xuboot Did you solve this problem? I have the same error.