---
license: mit
---
# ZINC-t5-v2 

We trained T5 on SMILES from ZINC using the task of masked-language modeling (MLM). Compared to ZINC-t5-v1, ZINC-t5-v2 uses a character-level tokenizer. This model can be used for the prediction of molecules' properties, reactions, or interactions with proteins by changing the way of finetuning.