Raj Movva

Hi, I'm wondering if it would be easy to add support for knowledge distillation for the Transformers on GLUE tasks (i.e. the TransformerSequenceClassifier module). I see that the distillation loss...

RAPIDS implementation of Scanpy rank_genes_groups appears incorrect

6

I tried running the RAPIDS implementation of rank_genes_groups alongside the Scanpy CPU implementation on the same data matrix, but I'm getting very different results. Here's my code for the GPU...

Anaconda installation ships with incorrect keras installation

3

Hi, I installed dragonn with "conda install dragonn -c kundajelab", but I got the following error message upon trying to train the example model: Traceback (most recent call last): File...

Hi, thank you for releasing this dataset. I'm doing some follow-up research with it, and wanted to perform the same quality filtering step that the paper mentions: > After all...

[RewardTrainer] Change print_rich_table parameters during Reward Model training

2

### Feature request The RewardTrainer has a default behavior of printing four chosen & rejected responses along with their logits at every validation iteration. This is implemented in the following...