Downloads · 30 days
364
9% of all-time downloads
BALM-paired
brineylab/BALM-paired
BALM-paired is a fill-mask model from brineylab. 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.
BALM-paired is an antibody language model that uses a RoBERTa architecture and was pre-trained on the ~1.6M paired antibody sequences from Jaffe et al. Datasets used for pre-training are available on Zenodo and code i…
All-time downloads
3.9K
Public
Parameters
304M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Dec 9, 2025
- Updated
- Dec 10, 2025
- SHA
- 78e6a592
Try a prompt
Model card
From the Hugging Face model README
BALM-paired
BALM-paired is an antibody language model that uses a RoBERTa architecture and was pre-trained on the ~1.6M paired antibody sequences from Jaffe et al. Datasets used for pre-training are available on Zenodo and code is available on GitHub. More details can be found in our paper published in Patterns.
Use
Load the model and tokenizer as follows:
from transformers import RobertaTokenizer, RobertaForMaskedLM
model = RobertaForMaskedLM.from_pretrained("brineylab/BALM-paired")
tokenizer = RobertaTokenizer.from_pretrained("brineylab/BALM-paired")
The tokenizer expects sequences formatted as: HEAVY_CHAIN</s>LIGHT_CHAIN.
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Dec 9, 2025
- Updated
- Dec 10, 2025