Closed likeboo closed 10 months ago
raise ValueError(f'Missing keys for inference: {missing_keys}.\nIf you still want to inference anyway, pass --force_inference to args.')
那个配置文件有问题,我修改了配置OK了 但是LORO好像不能加载。。
raise ValueError(f'Missing keys for inference: {missing_keys}.\nIf you still want to inference anyway, pass --force_inference to args.')
ValueError: Missing keys for inference: ['transformer.layers.0.attention.query_key_value.weight', 'transformer.layers.0.attention.query_key_value.bias', 'transformer.layers.0.attention.dense.weight', 'trans
former.layers.0.attention.dense.bias', 'transformer.layers.14.attention.query_key_value.weight', 'transformer.layers.14.attention.query_key_value.bias', 'transformer.layers.14.attention.dense.weight', 'transformer.layers.14.attention.dense.bias']. If you still want to inference anyway, pass --force_inference to args. 那个配置文件有问题,我修改了配置OK了 但是LORO好像不能加载。。
请问你是如何修改的latest配置文件?非常感谢! 我也报同样的错误:ValueError: could not find the metadata file checkpoints/checkpoints-XrayGLM-3000/latest, please check --load
Traceback (most recent call last): File "D:\AI\XrayGLM\web_demo.py", line 154, in
main(args)
File "D:\AI\XrayGLM\web_demo.py", line 90, in main
model, model_args = AutoModel.from_pretrained(
File "E:\anaconda3\envs\pytorch18\lib\site-packages\sat\model\base_model.py", line 275, in from_pretrained
model_cls = model_registry.get(args.model_class)
File "E:\anaconda3\envs\pytorch18\lib\site-packages\sat\model\registry.py", line 17, in get
raise ValueError(f'model_class {name} not found.')
ValueError: model_class FineTuneVisualGLMModel not found.
现有模型的配置文件不全吧。 我修改成VisualGLMModel类型后,又找不到 File "D:\AI\XrayGLM\web_demo.py", line 90, in main model, model_args = AutoModel.from_pretrained( File "E:\anaconda3\envs\pytorch18\lib\site-packages\sat\model\base_model.py", line 284, in from_pretrained load_checkpoint(model, args, load_path=model_path, prefix=prefix) File "E:\anaconda3\envs\pytorch18\lib\site-packages\sat\training\model_io.py", line 184, in load_checkpoint iteration, release, success = get_checkpoint_iteration(load_path) File "E:\anaconda3\envs\pytorch18\lib\site-packages\sat\training\model_io.py", line 152, in get_checkpoint_iteration raise ValueError('could not find the metadata file {}, please check --load'.format( ValueError: could not find the metadata file checkpoints\latest, please check --load
求解答,我是WINDOWS还没内有尝试自己微调。