按照P-Tuning教程准备微调本地的chatglm模型,训练的时候没有问题。但是在执行推理的时候出现错误。
RuntimeError: The size of tensor a (192) must match the size of tensor b (64) at non-singleton dimension 3
Expected Behavior
No response
Steps To Reproduce
按照P-Tuning教程执行bash train.sh之后,执行bash evaluate.sh出现问题
这里报错,报错信息如下:
RuntimeError: The size of tensor a (192) must match the size of tensor b (64) at non-singleton dimension 3
求大佬指导
Environment
- OS:Ubuntu 20.04
- Python:3.11
- Transformers:4.30.2
- PyTorch:2.0.1
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :True
Is there an existing issue for this?
Current Behavior
按照P-Tuning教程准备微调本地的chatglm模型,训练的时候没有问题。但是在执行推理的时候出现错误。 RuntimeError: The size of tensor a (192) must match the size of tensor b (64) at non-singleton dimension 3
Expected Behavior
No response
Steps To Reproduce
按照P-Tuning教程执行bash train.sh之后,执行bash evaluate.sh出现问题 这里报错,报错信息如下: RuntimeError: The size of tensor a (192) must match the size of tensor b (64) at non-singleton dimension 3 求大佬指导
Environment
Anything else?
No response