File size: 506 Bytes
56a3a08 b57fa29 |
1 2 3 4 5 6 7 |
---
license: apache-2.0
---
# ZINC-t5
This model is still under construction!!
We trained T5 on SMILES from ZINC using the task of masked-language modeling (MLM), and its tokenizer is also trained on ZINC data. This model can be used for the prediction of molecules' properties, reactions, or interactions with proteins by changing the way of finetuning. Here, we conducted a chemical reaction prediction, where if models were given a product, they generate reactants which is necessary for the reaction. |