Instructions to use afg1/RNAMamba-14M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use afg1/RNAMamba-14M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="afg1/RNAMamba-14M")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("afg1/RNAMamba-14M") model = AutoModel.from_pretrained("afg1/RNAMamba-14M", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
contrastive pretraining (pious-haze-45)
Andrew Green3987233 -
Reset to last good pretrained version
Andrew Green84f48a4 -
re-finetuned on deduplicated similarity data
Andrew Green579981a
-
Prototype after contrastive learning first pass. Unlikely to be good due to data duplication
Andrew Green519ad17 -
Updated pretrained model on 4 epochs (58,500 steps)
Andrew Green7341c83
-
Updated model with better pretraining. 30% MLM rate and shuffled source data
Andrew Greenc65927d -
Upload model
Verified signature10e91d9 -
Upload model
Verified signaturecd68b5d -
Upload model
Verified signature101372f -
Upload model
Verified signature79da6c6 -
Upload model
Verified signature9472c5e -
Upload model
Verified signatureb49ae26
-
Update README.md
Verified signature53e89e4 -
Move MLM readme into this repo.
Verified signaturebc15b88 -
Should be a base model with no MLM head
Andrew Greencb63d3a -
initial commit
Verified signatureedb8f38