Simon Levine

icon indicating a website link https://www.linkedin.com/in/simon-levine/

icon company Absci icon location San Francisco, CA icon location AI Scientist, Drug Discovery

Results 6 comments of Simon Levine

label_map.txt in dataset

Hi, As far as I know you will need to create a .txt for the free-text portion of your labels. That varies based on your source. You can check what...

multi-label classification / paperswithcode dataset

@OctoberChang please correct me if I'm wrong but I believe so, but you'll need to write preprocessing logic. I don't think your dataset would benefit from PIFA either if the...

Query synthesis

I've implemented [that paper](https://doi.org/10.1016/j.neucom.2014.06.042) at [simonlevine/membership-query-synthesis](https://github.com/simonlevine/membership-query-synthesis/blob/main/mqs_clf.ipynb) and plan to slowly adapt it properly to the ModAL API if anyone is interested for now.

Issue with Tokenizer (fast) splitting `<mask>` into constituent added special tokens despite mask token in vocab and in special tokens map

Thank you for your response @ArthurZucker . I would be happy to provide details about instantiation and behavior if needed.

Issue with Tokenizer (fast) splitting `<mask>` into constituent added special tokens despite mask token in vocab and in special tokens map

RobertaTokenizerFast

Discrepancies in Absolute Coordinates & Missing Side Chains in Output

Hi Patricia, not an author but have worked with this model. 1. It sounds like you are working on motif scaffolding. In this setting, the entire complex is initially translated...