ChemBERTa-100M-MLM

ChemBERTa model pretrained on a subset of 100M molecules from ZINC20 dataset using masked language modeling (MLM).

Usage

from transformers import AutoTokenizer, AutoModelForMaskedLM

tokenizer = AutoTokenizer.from_pretrained("DeepChem/ChemBERTa-100M-MLM")
model = AutoModelForMaskedLM.from_pretrained("DeepChem/ChemBERTa-100M-MLM")

Downloads last month: 17,478

Safetensors

Model size

92.1M params

Tensor type

F32