MoleBERT Tokenizer

This model is a molecular tokenizer trained on Nb-based TMC. From scratch, 400k train molecules, 30 epochs Test loss = 0.22 Code from: https://github.com/Rich-XGK/GTMGC

Usage

from models.mole_bert_tokenizer import MoleBERTTokenizerCollator, MoleBERTTokenizer
tokenizer = MoleBERTTokenizer.from_pretrained(...)

Downloads last month: 121

Safetensors

Model size

2.17M params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support