BiGamba (MEM, step 44000)

Repository: micanonsens/bigamba-cons_only-step44000

The Gamba models are a family of DNA language models from the ArGamba paper that jointly model DNA sequence and evolutionary rate information.

This repository includes the model weights and code for the Caduceus-based bidirectional variant model (BiGamba) trained to predict the Zoonomia 241-mammalian alignment-derived PhyloP scores using the Masked Evolutionary rate Modelling (MEM) task. For more details, see the GitHub repo.

Model family

All Gamba family models have checkpoints available at 44,000 steps:

Load

from transformers import AutoModel

model = AutoModel.from_pretrained(
    "micanonsens/bigamba-cons_only-step44000",
    trust_remote_code=True
)

Notes

• This repository includes custom modeling code; trust_remote_code=True is required.
• Ensure your environment has the necessary project dependencies installed (see GitHub).