shantanu nath

@bheinzerling I want to use BPEmb, but in your training [script](https://github.com/bheinzerling/bpemb/issues/5#issuecomment-481616023) you used sentencePiece for training and encoding . How can I use BPEmb model for data preprocessing?

As you can see the error is in the forward function. I actually didn't changed a lot in ViltForImagesAndTextClassification class. Here is my CustomModel: ``` class CustomModel(PreTrainedModel): def __init__(self, config):...

@alaradirik First of all, CustomModel is mainly meant to fix an existing issue. Because when I tried to fine-tune ViltForImagesAndTextClassification, I got above error. Then, I created customModel class as...

I don't know how to give u minimal code example, I describe before what I wanted to do. if u try to fine-tune ViltForImagesAndTextClassification with 10 images instead of 2,...

@LoveLetter1 Sorry for being late. Yes. lmk if you still need any help.

@vdobrovolskii. I have similar issue during train and evaluate. It's just stuck without showing any error.

@vdobrovolskii The outcome from ```pip freeze``` ```attrs==23.1.0 certifi @ file:///croot/certifi_1671487769961/work/certifi charset-normalizer==3.1.0 click==8.1.3 filelock==3.12.0 idna==3.4 importlib-metadata==6.6.0 joblib==1.2.0 jsonlines==3.1.0 numpy==1.21.6 packaging==23.1 Pillow==9.5.0 regex==2023.5.5 requests==2.31.0 sacremoses==0.0.53 sentencepiece==0.1.91 six==1.16.0 tokenizers==0.8.1rc2 toml==0.10.2 torch==1.4.0+cu92 torchvision==0.5.0+cu92 tqdm==4.65.0...

@vdobrovolskii I am not even able to evaluate here in this machine. Loading Bert model is really slow.

@vdobrovolskii These are the steps I followed starting from data processing. You can see I am able to run the evaluation for Test set. But the result doesn't seem accurate....

@vdobrovolskii Regarding this problem. Can you please tell me the ```sentencepiece``` version?