Dan Ofer
Dan Ofer
Any plans to allow openCL support? (Given that other neural art style algorithms in Torch support it). Thanks!
Any chance you will upload the trained, final model? Thanks!
Hi, What would be needed in order to add support for ProteinBert embeddings? (The framework/package is written with Keras/TF, and also supports GO annotations): https://github.com/nadavbra/protein_bert
Is there any way to directly load the ESM models with the HF Transformers (or similarly compatible) libraries? e.g. with `AutoModelForTokenClassification`? Thanks! (I want to do finetuning, and to use...
Silly question: How should new data be formatted, in order to learn/predict over it? Assuming I have sentences and a label for each sentence. (I didn't see labels in the...
Hi, I'm trying to run the "example" on my own data. After fitting the tokenizer, I get a big, long list of error messages from Theano. Background: Windows 8.1. Anaconda...
The current Benchmark Tasks lack any results, dataset details and most importantly results. If they're all empty, page should be renamed "example tasks" at least. https://ohdsi.github.io/PatientLevelPrediction/articles/BenchmarkTasks.html
1. Nice resource! I may add some to it in future (although the ones I use for benchmarking are considerably "rarer" than the ones here - time-series + raw text...
Some code is missing from the winner’s submission; https://github.com/rapidsai/deeplearning/tree/main/WSDM2021/02_Models/XLNet_SMF Good stuff overall! Congrats!
Hi, I'm interested in trying your framework + replicating your results (especially on the second, "long range" dataset you added). Where is the data available? (Both yours and the Troyanskaya...