How should I get the tensor from a piece of text for a given dataset?

[QinSY123]

In the sample code, the input for the text is a random tensor, how should I get this tensor from a piece of text for a given dataset? text = torch.randint(0, 49408, (4, 256)).cuda()

[krrishdholakia]

Are you using a specific dataset or is this a general approach?

You could use a pre-trained model like BERT for this.

Let me know if that helps!

• Clerkie (https://clerkie.co/)

[QinSY123]

Are you using a specific dataset or is this a general approach?

You could use a pre-trained model like BERT for this.

Let me know if that helps!

• Clerkie (https://clerkie.co/)

Thanks a lot!

[xiefei1026]

Hello, have you solved this problem? I have the same problem