Language Translation with Multi-Head Attention | Transformers from Scratch

[@ebadsayed487]

When I am running the 49th line for training the model, it gives me an attribute error ValueError: Only input tensors may be passed as positional arguments. The following argument value should be passed as a keyword argument: True (of type ) Can you resolve this please?

[@kaleseyuh]

Amazing! I want to train a model to translate a low-resource language. Would this tutorial work?

[@DevelopersHutt]

It should. Give it a try

[@AriKath]

Incredibale!

[@efoanopa]

I would like to know... Why is it that in the get_angles function, you floor-divided i by 2? That part np.power(10000, 2 * (i//2)/dmodel)

[@DevelopersHutt]

I'm glad you asked! That's for positional encoding. You can find the context here.kzbin.info/www/bejne/bGfWlnyKpMqaq6csi=mX83N2ETA1DFOVu- If you still struggle understanding it, drop me a line

[@efoanopa]

@@DevelopersHutt, you see in the formular, it was just 2*i But you made it 2*(i//2) and I am finding it difficult to understand why

[@efoanopa]

@@DevelopersHutt also, can you please send a link to your code?

[@souhail_lh3013]

can you please send a link to your code?

[@abhishek171278]

can you share code repo

[@DevelopersHutt]

github.com/developershutt/Transformers-in-action