Downloads · 30 days
6
35% of all-time downloads
sns-paper-flashzoi-rf32k
tanaylab/sns-paper-flashzoi-rf32k
sns-paper-flashzoi-rf32k is a machine learning model from tanaylab. 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 apache-2.0.
Borzoi architecture trained from random initialization on mouse ESC-derived CUT&Tag H3K27me3 and H3K4me3 tracks.
All-time downloads
17
Public
Parameters
192M
768 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors768 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026
- SHA
- e8cd95d2
Datasets
Model card
From the Hugging Face model README
Flashzoi RF 32k — Trained from Scratch
Borzoi architecture trained from random initialization on mouse ESC-derived CUT&Tag H3K27me3 and H3K4me3 tracks.
- Receptive field: 32k
- Architecture: Borzoi (from scratch, model name "flashzoi")
- Resolution: 32 bp
- Training data: Normalized CUT&Tag from mouse ESC-derived embryoid bodies
- Paper: Casimov, Lifshitz et al., "Reverse engineering the genomic encodings of the pluripotent epigenome"
Usage
torchrun --nproc_per_node=8 infer_borzoi_pytorch.py \
--config config.yaml \
--checkpoint model.safetensors \
--genome_fasta mm10.fa \
--output_dir predictions/
See the paper companion repository for full code and configs.
- License
- apache-2.0
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026