Downloads · 30 days
32
30% of all-time downloads
PlantHelixSeek-translation_onoff
zhangtaolab/PlantHelixSeek-translation_onoff
PlantHelixSeek-translation_onoff is a text classification model from zhangtaolab. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
Fine-tuned checkpoint of PlantHelixSeek (470M parameters) for binary classification of translation on/off state.
All-time downloads
106
Public
Parameters
471M
1.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.9 GB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- HelixSeek
- Access
- Public
- Created
- Jul 19, 2026
- Updated
- Nov 5, 2026
- SHA
- 21b16e10
Try a prompt
Base models
Model card
From the Hugging Face model README
PlantHelixSeek-translation_onoff
Fine-tuned checkpoint of PlantHelixSeek (470M parameters) for binary classification of translation on/off state.
Task
- Type: binary classification of translation on/off state
- Label: 0 = off, 1 = on
- Input length: 500 bp
- Dataset: cross_species_leaf_on_off_translation
Dataset and splits
The checkpoint uses the released train.csv, dev.csv and test.csv splits of cross_species_leaf_on_off_translation (21,894 / 5,492 / 39,035 sequences). The source of the dataset is described on its dataset card.
Training
| Setting | Value |
|---|---|
| Base model | PlantHelixSeek-470M |
| Epochs | 3 |
| Learning rate | 2e-5 |
| Per-device batch size | 3 |
| Gradient accumulation | 5 |
| Effective batch size | 15 |
| Warm-up ratio | 0.1 |
| Weight decay | 0.01 |
| Scheduler | linear |
| Optimizer | AdamW (fused) |
| Precision | bf16 |
| Gradient clipping | 1.0 |
| Seed | 42 |
| Hardware | one NVIDIA GPU |
| Training loss | 0.443 |
| Training time | 0.3 h |
Held-out validation metrics
Metrics on the held-out dev.csv split (the split used for checkpoint selection).
| Metric | Value |
|---|---|
| f1 | 0.810 |
| AUROC | 0.805 |
| AUPRC | 0.875 |
| mcc | 0.439 |
| accuracy | 0.748 |
Usage
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained(
"zhangtaolab/PlantHelixSeek-translation_onoff", trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
"zhangtaolab/PlantHelixSeek-translation_onoff", trust_remote_code=True
)
Always pass trust_remote_code=True; the HelixSeek architecture is registered through the Hugging Face auto_map mechanism.
Citation
Wu Y, He Y, Chen L, Liu Y, Wang T, Zhao H, Zhang Y, Zhang T. PlantHelixSeek learns transferable genome representations that capture conserved genome grammar for functional interpretation across plant species. Molecular Plant, 2026. Manuscript MOLECULAR-PLANT-D-26-00999 (DOI to be assigned).
Dataset source: Zhai et al., Cell Genomics 2026, doi:10.1016/j.xgen.2026.101329.
License
CC-BY-NC 4.0 (research use; contact the authors for commercial licensing).
- Task
- Text Classification
- Library
- transformers
- Type
- HelixSeek
- License
- cc-by-nc-4.0
- Created
- Jul 19, 2026
- Updated
- Nov 5, 2026