BLEURT-20

Para instalar el modelo y realizar predicciones, utilice el siguiente comando y código en Python:

pip install git+https://github.com/lucadiliello/bleurt-pytorch.git

import torch
from bleurt_pytorch import BleurtConfig, BleurtForSequenceClassification, BleurtTokenizer

config = BleurtConfig.from_pretrained('lucadiliello/BLEURT-20')
model = BleurtForSequenceClassification.from_pretrained('lucadiliello/BLEURT-20')
tokenizer = BleurtTokenizer.from_pretrained('lucadiliello/BLEURT-20')

references = ["a bird chirps by the window", "this is a random sentence"]
candidates = ["a bird chirps by the window", "this looks like a random sentence"]

model.eval()
with torch.no_grad():
    inputs = tokenizer(references, candidates, padding='longest', return_tensors='pt')
    res = model(**inputs).logits.flatten().tolist()
    print(res)
# [0.9990496635437012, 0.7930182218551636]

Para más detalles sobre la configuración del modelo y las clases, puede consultar el repositorio de BLEURT en PyTorch.