Patrick Yu

First of all, thanks for the great resource to help people get started with prompt tuning! I was wondering as to why prompt tuning uses more memory & time than...

As I am currently using your great library extensively - I was wondering, what are the main feature differences between your dataloader and the one provided by the original meta-dataset...

Sampling from episodic loader gives error - "Key image doesn't exist (select from [])!"

2

When sampling from the episodic loader, all usually goes fine until I get the following error: ``` Traceback (most recent call last): File "/home/patrick/pytorch-meta-dataset/pytorch_meta_dataset/pipeline.py", line 145, in get_next sample_dic =...

Extract gene-level embeddings from scGPT?

3

Is there a way to extract gene-level embeddings from scGPT? I believe there's a way to access the cell embedding, but not sure how the gene-level embedding is defined. Just...

Future compatibility with Transformers API?

6

Thanks for the great work! I was wondering if there's any plans to integrate your scGPT model with the Transformers (https://huggingface.co/docs/transformers/index) API? I'm asking because the project workflow I use...

How to modify scANVI to handle continuous cell labels?

1

**Is your feature request related to a problem? Please describe.** Not a problem - mainly clarification questions. I am wondering how to modify scANVI to handle continuous prediction tasks. Currently,...