kekayan

@bjchaudhari29 try this to load the model. ```from models.tabformer_bert import TabFormerBertConfig config = TabFormerBertConfig.from_pretrained( "/output/checkpoint-2000/config.json" ) model = tab_net.model.from_pretrained("/output/checkpoint-2000/pytorch_model.bin", config=config ,vocab=dataset.vocab).to(device)

Hi @ink-pad , Thanks for open-sourcing the code. I have a question, Do we need to change the line [118 in tabformer_bert.py](https://github.com/IBM/TabFormer/blob/main/models/tabformer_bert.py#L118), from `outputs = (prediction_scores,) + outputs[2:]` to `outputs...

sure, I will do the changes now

pushed the change as you suggested @hwchase17