CaiJichang
CaiJichang
Thank you very much for open sourcing the QCNN code. Since your code was open sourced 2 years ago, in order to run your code correctly I need to know...
I see this todo list: Find good dataset for GPT-like models to evaluate knowledge neurons (PARAREL isn't applicable since the tail entities aren't always at the end of the sentence)...
Traceback (most recent call last): File "train_spt.py", line 18, in from model.vision_transformer_timm import VisionTransformerSepQKV File "/home/lyc/TNTprojectz/KE/SPT/model/__init__.py", line 2, in from .swin_transformer import * ModuleNotFoundError: No module named 'model.swin_transformer'  
Does SPT support the selection of sensitive parameters in LLMS? Very excited to see your work, I want to migrate your work to LLM, How can I change the code?...