Description
What is your question?
问题：模型微调后加载时出错
Question: Error loading inference after model fine-tuning
RuntimeError: SequenceLabelingPipeline: SequenceLabelingModel: Error(s) in loading state_dict for SequenceLabelingModel:
Missing key(s) in state_dict: "embedder.transformer_model.embeddings.position_ids".
What have you tried?
我完全按照官方教程进行的微调，没有进行额外的代码修改，自动保存的微调模型无法加载。
I completely followed the official tutorial for fine-tuning without making any additional code modifications, and the automatically saved fine-tuning model cannot be loaded.
Code (if necessary)
Code:
python```
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
p = pipeline(
Tasks.named_entity_recognition,
'/root/experiments/experiments/CMeEE-cmeee/20240227_093521/output_best'
)
result = p('对儿童SARST细胞亚群的研究表明，与成人SARS相比，儿童细胞下降不明显，证明上述推测成立。')
print(result)
### What's your environment?
- AdaSeq Version (e.g., 1.0 or master): 0.6.6
- ModelScope Version (e.g., 1.0 or master): 1.12.0
- PyTorch Version (e.g., 1.12.1): 2.2.1
- OS (e.g., Ubuntu 20.04): Ubuntu 20.04
- Python version: 3.11
- CUDA/cuDNN version:
- GPU models and configuration: RTX3090
- Any other relevant information:
### Code of Conduct
- [X] I agree to follow this project's Code of Conduct