FungiHelixSeek
Collection
18 items โข Updated
How to use zhangtaolab/FungiHelixSeek-H3 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-classification", model="zhangtaolab/FungiHelixSeek-H3", trust_remote_code=True) # pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForSequenceClassification
model = AutoModelForSequenceClassification.from_pretrained("zhangtaolab/FungiHelixSeek-H3", trust_remote_code=True, device_map="auto")Fine-tuned model of the FungiHelixSeek fungal DNA foundation model for histone mark H3 region prediction (GUE EMP benchmark, S. cerevisiae ChIP-chip).
| Property | Value |
|---|---|
| Task | Binary sequence classification (500 bp windows) |
| Base model | FungiHelixSeek (470M, MLM) |
| Dev best accuracy / F1 | 0.9022 |
| Training | 3 epochs, lr 2e-5, single NVIDIA GPU |
| Dataset | fungi-histone-modifications subset H3 |
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained(
"zhangtaolab/FungiHelixSeek-H3", trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("zhangtaolab/FungiHelixSeek-H3", trust_remote_code=True)
Train/dev/test splits: fungi-histone-modifications (subset H3) ยท ModelScope
CC-BY-NC 4.0 (research use; contact authors for commercial licensing).