Xue xuanyu

Why is the accuracy of classification tasks on dataset(sst2) using this model(state-spaces/mamba-370m-hf) only 0.7?

1

I can reach the accuracy of 0.93 just after changing the base model into google-bert/bert-base-uncased model. I download the model(state-spaces/mamba-370m-hf) from https://huggingface.co/state-spaces/mamba-370m-hf. And here's my code: # Training a Classification...