Chen Qian

@abheesht17 Thanks for opening this feature request! Yes, autoregressive generation is something we are looking to add. We will need some discussions on which technique we want to support (greedy...

@monatis Sorry, somehow I missed your message... We are actively working on determining the input/output format and in which form text decoding is supported. Once we are ready, we will...

Training config: | MODEL NAME | NUM LAYERS(L) | HIDDEN SIZE(H) | NUM HEADS(A) | BATCH_SIZE | NUM TRAIN STEPS | |------------|---------------|----------------|--------------|------------|-----------------| | BERT SMALL | 4 | 512 |...

Training config: | MODEL NAME | NUM LAYERS(L) | HIDDEN SIZE(H) | NUM HEADS(A) | BATCH_SIZE | NUM TRAIN STEPS | |------------|---------------|----------------|--------------|------------|-----------------| | BERT SMALL | 4 | 512 |...

We fixed some initialization issues, and reran the experiment, it gets closer to the official reported score. Training config: | MODEL NAME | NUM LAYERS(L) | HIDDEN SIZE(H) | NUM...

@abheesht17 Thanks for opening this feature request! Yes, having an adversarial attack system would be nice for model evaluation. Our current problem is that we do not have pretrained model...

Thanks! I am not very familiar with Regex, is it possible to set split pattern as (default split pattern - "\[" - "\]")?

@DavidLandup0 Thank you for reporting the issue! To clarify, the saving/loading works with Keras saved model format, but breaks with h5 format. I checked the error, and it implies `TokenAndPositionEmbedding`...

@jessechancy Thanks!

/gcbrun