Downloads · 30 days
26.3K
13% of all-time downloads
ChemBERTa-100M-MLM
DeepChem/ChemBERTa-100M-MLM
ChemBERTa-100M-MLM is a fill-mask model from DeepChem. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as mit.
ChemBERTa model pretrained on a subset of 100M molecules from ZINC20 dataset using masked language modeling (MLM).
All-time downloads
200K
Public
Parameters
92.1M
369 MB on disk
Likes
9
Public
Repo makeup
Click a slice to open those files.
.safetensors369 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- May 9, 2025
- Updated
- Aug 18, 2025
- SHA
- f5c45f44
Try a prompt
Spaces
Model card
From the Hugging Face model README
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")
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- License
- mit
- Hf Inference
- live
- Created
- May 9, 2025
- Updated
- Aug 18, 2025