pytorch-original-transformer
pytorch-original-transformer copied to clipboard
gordicaleksa
My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pret...
Hi, thanks for your repo: helps a lot! In the paper weight matrix is shared between the two embedding layers and the pre-softmax linear transformation. "In our model, we share...
Not sure what is going on here but the best that I can tell is that there is a gzip file that seems to be missing. Thank You Tom Traceback...
downloading de-en.tgz File "training_script.py", line 103, in train_transformer train_token_ids_loader, val_token_ids_loader, src_field_processor, trg_field_processor = get_data_loaders( tarfile.ReadError: not a gzip file
What does the frequency represent in positional encoding ? Why do we need to multiply it with the positional values? frequencies = torch.pow(10000., -torch.arange(0, model_dimension, 2, dtype=torch.float) / model_dimension)
While running `def translate_a_single_sentence(translation_config):` I have encountered an error in which the file en-de.tgz is not recognized as a gzip file. How could I do? Below, it is reported the...
hi! thanks for your repo,can you show the bleu for this repo on WMT14 dataset?
# Data manipulation related imports from torchtext.data import Dataset, BucketIterator, Field, Example from torchtext.data.utils import interleave_keys from torchtext import datasets from torchtext.data import Example imports under this are not working...
Thanks for your work. I met some problem about conda environment creating. The error as follow. Please tell me how to solve thie problem. ``` $ conda env create Channels:...
Metadata
Owner
Metadata
My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pret...