metadata
license: apache-2.0
RNAElectra
RNAElectra is a pretrained RNA language model for nucleotide-level sequence representation learning.
Load model
import torch
from transformers import AutoModel
from tokenizer import NucEL_Tokenizer
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModel.from_pretrained(
"FreakingPotato/RNAElectra",
trust_remote_code=True
).to(device)
tokenizer = NucEL_Tokenizer.from_pretrained(
"FreakingPotato/RNAElectra",
trust_remote_code=True
)
sequence = "AUGCAUGCAUGCAUGC"
inputs = tokenizer(sequence, return_tensors="pt")
inputs = {k: v.to(device) for k, v in inputs.items()}
with torch.no_grad():
outputs = model(**inputs)
embeddings = outputs.last_hidden_state
print(embeddings.shape)