Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.
Apache License 2.0
301
stars
117
forks
source link
AssertionError: <None> should be a PretrainedModel class, but <<class 'NoneType'>> #571
Traceback (most recent call last):
File "/home/aistudio/work/paddlemix/supervised_finetune.py", line 195, in
main()
File "/home/aistudio/work/paddlemix/supervised_finetune.py", line 76, in main
model_config = AutoConfigMIX.from_pretrained(model_args.model_name_or_path, dtype=dtype) # freeze_mm_mlp_adapter
File "/home/aistudio/work/paddlemix/paddlenlp/transformers/auto/configuration.py", line 243, in from_pretrained
config_class = cls._get_config_class_from_config(pretrained_model_name_or_path, resolved_config_file)
File "/home/aistudio/work/paddlemix/auto/configuration.py", line 99, in _get_config_class_from_config
assert inspect.isclass(model_class) and issubclass(
AssertionError: should be a PretrainedModel class, but <<class 'NoneType'>>
Traceback (most recent call last): File "/home/aistudio/work/paddlemix/supervised_finetune.py", line 195, in
main()
File "/home/aistudio/work/paddlemix/supervised_finetune.py", line 76, in main
model_config = AutoConfigMIX.from_pretrained(model_args.model_name_or_path, dtype=dtype) # freeze_mm_mlp_adapter
File "/home/aistudio/work/paddlemix/paddlenlp/transformers/auto/configuration.py", line 243, in from_pretrained
config_class = cls._get_config_class_from_config(pretrained_model_name_or_path, resolved_config_file)
File "/home/aistudio/work/paddlemix/auto/configuration.py", line 99, in _get_config_class_from_config
assert inspect.isclass(model_class) and issubclass(
AssertionError: should be a PretrainedModel class, but <<class 'NoneType'>>