Jaap Jumelet
Jaap Jumelet
Hi! I've been working with your IH/IG implementation lately, and doing some experiments with it in an NLP context. What I have noticed is that when I increase the length...
**Describe the bug** I'm trying to convert a PyTorch LSTM model to Tensorflow via ONNX. The conversion from PyTorch to ONNX runs smoothly without problems, and obtaining a `tf_rep` via...
One thing I was unsure about is how to split up model performance on individual subtasks: within BLiMP it would be a bit odd to just merge all accuracies together...
## Description When computing attributions for a list of sentences the tqdm iterator prints out the iteration per token, which gives no insight into how far in you are with...