search

HHousen / TransformerSum

Models to perform neural summarization (extractive and abstractive) using machine learning transformers and a tool to convert abstractive summarization datasets to the extractive task.
https://transformersum.rtfd.io
GNU General Public License v3.0
427 stars 58 forks source link

Problem in cloning repository mentioned in documentation to train an abstractive summarization model #43

Closed silentghoul-spec closed 3 years ago

silentghoul-spec commented 3 years ago

Hi, I can't install pip install git+https://github.com/HHousen/transformers.git@longformer_encoder_decoder and pip install git+https://github.com/allenai/longformer.git@encoderdecoder. It's saying repository doesn't exist. Can you please correct the path of github directories?

HHousen commented 3 years ago

@silentghoul-spec Thanks for reporting this. This is because huggingface/transformers recently updated to version 4.2.0, which added support for the LongformerEncoderDecoder. The LED is now an official model on the huggingface/transformers documentation. Thus, it can now be used with the abstractive training code by specifying --model_name_or_path allenai/led-base-16384.

silentghoul-spec commented 3 years ago

Thanks for answering 😇

HHousen commented 3 years ago

Let me know if there are any issues with the new implementation.