|
---
|
|
license: apache-2.0
|
|
---
|
|
|
|
## Model Overview
|
|
|
|
PlantCaduceus is a DNA language model pre-trained on 16 Angiosperm genomes. Utilizing the Caduceus architecture and a masked language modeling objective, PlantCaduceus is designed to pre-train genomic sequences from 16 species spanning a history of 160 million years. We have trained a series of PlantCaduceus models with varying parameter sizes:
|
|
|
|
- **PlantCaduceus_l20**: 20 layers, 384 hidden size, 20M parameters
|
|
- **PlantCaduceus_l24**: 24 layers, 512 hidden size, 40M parameters
|
|
- **PlantCaduceus_l28**: 28 layers, 768 hidden size, 112M parameters
|
|
- **PlantCaduceus_l32**: 32 layers, 1024 hidden size, 225M parameters
|
|
|
|
## How to use
|
|
```python
|
|
from transformers import AutoModel, AutoModelForMaskedLM, AutoTokenizer
|
|
model_path = 'maize-genetics/PlantCaduceus_l20'
|
|
device = "cuda:0" if torch.cuda.is_available() else "cpu"
|
|
model = AutoModelForMaskedLM.from_pretrained(model_path, trust_remote_code=True).to(device)
|
|
model.eval()
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
|
|
|
sequence = "ATGCGTACGATCGTAG"
|
|
encoding = tokenizer.encode_plus(
|
|
sequence,
|
|
return_tensors="pt",
|
|
return_attention_mask=False,
|
|
return_token_type_ids=False
|
|
)
|
|
input_ids = encoding["input_ids"].to(device)
|
|
with torch.inference_mode():
|
|
outputs = model(input_ids=input_ids, output_hidden_states=True)
|
|
``` |
