Instructions to use Taykhoom/RNABERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Taykhoom/RNABERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Taykhoom/RNABERT", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("Taykhoom/RNABERT", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Evaluating RNABERT biological transfer
#1
by Shicheng - opened
Your RNABERT port preserves all seven backbone representation levels against the original weights while exposing a compact six-layer RNA encoder through Transformers. Which downstream evaluation would you consider most informative for biological transfer: structural alignment, non-coding RNA family classification, or variant-effect prediction on sequences outside the Rfam pretraining distribution?