PlantHelixSeek-sequence_conservation

Fine-tuned checkpoint of PlantHelixSeek (470M params) for Sequence conservation prediction.

Task

• Type: binary
• Dataset: plant-multi-species-sequence-conservation · ModelScope

Training

• Base model: PlantHelixSeek
• Epochs: 3
• Train loss: 0.20310962256769396

Usage

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained(
    "zhangtaolab/PlantHelixSeek-sequence_conservation", trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
    "zhangtaolab/PlantHelixSeek-sequence_conservation", trust_remote_code=True
)

Always pass trust_remote_code=True — the HelixSeek architecture is registered via HuggingFace auto_map.

License

CC-BY-NC 4.0 (research use; contact authors for commercial licensing)