Downloads · 30 days
6
29% of all-time downloads
sns-paper-borzoi-finetuned-rf2k
tanaylab/sns-paper-borzoi-finetuned-rf2k
sns-paper-borzoi-finetuned-rf2k 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.
Pre-trained Borzoi model (johahi/borzoi-replicate-0) fine-tuned on mouse ESC-derived CUT&Tag H3K27me3 and H3K4me3 tracks via two-stage training (linear probe then full fine-tuning).
All-time downloads
21
Public
Parameters
186M
744 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors744 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026
- SHA
- 044dec13
Datasets
Model card
From the Hugging Face model README
Borzoi Fine-tuned RF 2k — Foundation Model
Pre-trained Borzoi model (johahi/borzoi-replicate-0) fine-tuned on mouse ESC-derived CUT&Tag H3K27me3 and H3K4me3 tracks via two-stage training (linear probe then full fine-tuning).
- Receptive field: 2k
- Base model:
johahi/borzoi-replicate-0 - 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