metadata
datasets:
- genbio-ai/rna-downstream-tasks
base_model:
- genbio-ai/rnafm-1.6b-cds
5-fold cross-validation LoRA fine-tuned checkpoints for protein abundance prediction (hsapiens).
How to Use
Download model
from huggingface_hub import snapshot_download
from pathlib import Path
model_name = "genbio-ai/rnafm-1.6b-cds-protein-abundance-hsapiens-ckpt"
genbio_models_path = Path.home().joinpath('genbio_models', model_name)
genbio_models_path.mkdir(parents=True, exist_ok=True)
snapshot_download(repo_id=model_name, local_dir=genbio_models_path)
Load model for inference
from genbio_finetune.tasks import SequenceRegression
ckpt_path = genbio_models_path.joinpath('fold0', 'model.ckpt')
model = SequenceRegression.load_from_checkpoint(ckpt_path, strict_loading=False).eval()
collated_batch = model.collate({"sequences": ["ACGT", "AGCT"]})
logits = model(collated_batch)
print(logits)