WenXIN-AI

qwen‘s tokenizer problem?

[notebookbdffc79b63.zip](https://github.com/user-attachments/files/16644301/notebookbdffc79b63.zip) this is my notebook on kaggle, engine is too large so I can't submit it . if run the notebook, you can get same result

pip install tensorrt print(trt.__version__) import tensorrt #load model import torch import torchvision.models as models model= models.resnet50(pretrained=True) import tensorrt as trt import torch import torchvision.models as models from torchvision.models import ResNet50_Weights...