Downloads · 30 days
0
Melchior
elonlit/Melchior
Melchior is a machine learning model from elonlit. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This model combines the strengths of selective state spaces (Mamba) and transformers for accurate RNA basecalling. It achieves SOTA accuracy while maintaining efficient inference speeds through its hybrid architecture…
Access
Public
Updated Jan 21, 2025
Repo size
37.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.ckpt36.7 GB · 99%
At a glance
- License
- mit
- Access
- Public
- Created
- Jan 1, 2025
- Updated
- Jan 21, 2025
- SHA
- ad3ed62b
Model card
From the Hugging Face model README
Melchior
This model combines the strengths of selective state spaces (Mamba) and transformers for accurate RNA basecalling. It achieves SOTA accuracy while maintaining efficient inference speeds through its hybrid architecture, with further advantages described in the paper.
Model Details
- Model Type: Hybrid Mamba-Transformer
- Task: RNA Basecalling
- Parameters: 134M
- Architecture: isotropic 20-layer alternating Mamba and MHA backbone, with 8 attention heads
- Framework: PyTorch
Training
- Training dataset: Arabidopsis thaliana, Homo sapiens, Caenorhabditis elegans, Escherichia coli, and synthetic constructs from Epinano
- Hardware used: One A100
- Training time: 9 days
- Optimization: Adam, stochastic weight averaging, linear warmup followed by cosine decay
See full code at github.com/elonlit/Melchior.
Citation
@article{melchior2025,
title={Melchior: A Hybrid Mamba-Transformer RNA Basecaller},
author={Litman, Elon},
journal={bioRxiv preprint bioRxiv:2025.01.11.632456},
year={2025}
}
License
MIT
Contact
For any inquiries, contact [email protected].
- License
- mit
- Languages
- en
- Created
- Jan 1, 2025
- Updated
- Jan 21, 2025