frederikkemarin / BEND

Benchmarking DNA Language Models on Biologically Meaningful Tasks
BSD 3-Clause "New" or "Revised" License
90 stars 13 forks source link

Add DNABERT-2 #14

Closed fteufel closed 1 year ago

fteufel commented 1 year ago

Need to find out how to best handle chunking for embedding.

frederikkemarin commented 1 year ago

Don't we already have a chunking mechanism in the other embedders? or is this not efficient for DNABERT-2?

fteufel commented 1 year ago

https://github.com/Zhihan1996/DNABERT_2/issues/2