Johannes Tammekänd

Hi, I'd like to propose [NFTPort](https://nftport.xyz) as developer tooling for communicating with Ethereum via APIs to be added to [Recommended tools](https://nftschool.dev/reference/recommended-tools/#test-blockchain-tools). Specifically, devs can pull all NFT data from NFTPort's...

ELMo word embeddings

1

Have you thought of adding ELMo word embeddings to the selection? It outperforms both GloVe and Word2Vec embeddings. Link to ELMo: https://github.com/allenai/allennlp/blob/master/tutorials/how_to/elmo.md Implementation with Keras: https://towardsdatascience.com/elmo-embeddings-in-keras-with-tensorflow-hub-7eb6f0145440

Validation accuracy & Mobilenet

9

Hi, Thank you for the rewrite and very intuitive repo. Have you reported validation accuracy for the Resnet50 and have you also implemented mobilenet? Thanks, Johannes

Extractive summarization with raw text input not working

11

Extractive summarization with raw text input returns the same text until the first CLS separator. Model: CNN/DM Extractive Command to reproduce: ``` python3 train.py -task ext -mode test_text -test_from /home/ubuntu/PreSumm/models/bertext_cnndm_transformer.pt...

In data generator, qa0 (all tasks) = AllTasks: https://github.com/MostafaDehghani/bAbI-T2T/blob/master/t2t_usr_dir/babi_qa.py#L414 This also seems to be the preferred way in tensor2tensor: https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/data_generators/babi_qa.py#L468

Hi, Hope all is well and thank you for well-written paper! Are you planning to open-source your pretrained models as well? Thanks, Johannes

Tensor2Tensor compatibility

3

Thank you for such easy to read code & repo - can be seen that a lot of hard work has gone into it! Secondly, found your work from Sebastian...

Hey! Thank You for the wonderful work. Had a quick question - is it possible to run multiple instances of the bot on the same machine? Thanks and take care,...