MiniDNA small model

This is a distilled version of DNABERT by using MiniLM technique. It has a BERT architecture with 6 layers and 384 hidden units, pre-trained on 6-mer DNA sequences. For more details on the pre-training scheme and methods, please check the original thesis report..

How to Use

The model can be used to fine-tune on a downstream genomic task, e.g. promoter identification.

import torch
from transformers import BertForSequenceClassification
model = BertForSequenceClassification.from_pretrained('Peltarion/dnabert-minilm-small')

More details on how to fine-tune the model, dataset and additional source codes are available on github.com/joanaapa/Distillation-DNABERT-Promoter.

Downloads last month
41
Inference API
Unable to determine this model’s pipeline type. Check the docs .