AIDO.DNA-300M / README.md
probablybots's picture
Update README.md
403475c verified
|
raw
history blame
1.92 kB

AIDO.DNA

For a more detailed description, refer to the SOTA model in this collection https://huggingface.co/genbio-ai/dnafm-7b

How to Use

Build any downstream models from this backbone

Embedding

from genbio_finetune.tasks import Embed
model = Embed.from_config({"model.backbone": "dna300m"}).eval()
collated_batch = model.collate({"sequences": ["ACGT", "AGCT"]})
embedding = model(collated_batch)
print(embedding.shape)
print(embedding)

Sequence Level Classification

import torch
from genbio_finetune.tasks import SequenceClassification
model = SequenceClassification.from_config({"model.backbone": "dna300m", "model.n_classes": 2}).eval()
collated_batch = model.collate({"sequences": ["ACGT", "AGCT"]})
logits = model(collated_batch)
print(logits)
print(torch.argmax(logits, dim=-1))

Token Level Classification

import torch
from genbio_finetune.tasks import TokenClassification
model = TokenClassification.from_config({"model.backbone": "dna300m", "model.n_classes": 3}).eval()
collated_batch = model.collate({"sequences": ["ACGT", "AGCT"]})
logits = model(collated_batch)
print(logits)
print(torch.argmax(logits, dim=-1))

Regression

from genbio_finetune.tasks import SequenceRegression
model = SequenceRegression.from_config({"model.backbone": "dna300m"}).eval()
collated_batch = model.collate({"sequences": ["ACGT", "AGCT"]})
logits = model(collated_batch)
print(logits)

Or use our one-liner CLI to finetune or evaluate any of the above!

gbft fit --model SequenceClassification --model.backbone dna300m --data SequenceClassification --data.path <hf_or_local_path_to_your_dataset>
gbft test --model SequenceClassification --model.backbone dna300m --data SequenceClassification --data.path <hf_or_local_path_to_your_dataset>

For more information, visit: Model Generator