DeBERTinha XSmall for Semantic Textual Similarity

Full regression example

from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoConfig
import numpy as np
import torch

model_name = "sagui-nlp/debertinha-ptbr-xsmall-assin2-sts"
s1 = "A gente faz o aporte financeiro, é como se a empresa fosse parceira do Monte Cristo."
s2 = "Fernando Moraes afirma que não tem vínculo com o Monte Cristo além da parceira."
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
config = AutoConfig.from_pretrained(model_name)
model_input = tokenizer(*([s1], [s2]), padding=True, return_tensors="pt")
with torch.no_grad():
    output = model(**model_input)
    score = output[0][0].detach().numpy().item()
    print(f"Similarity Score: {np.round(float(score), 4)}")

Citation

@misc{campiotti2023debertinha,
      title={DeBERTinha: A Multistep Approach to Adapt DebertaV3 XSmall for Brazilian Portuguese Natural Language Processing Task}, 
      author={Israel Campiotti and Matheus Rodrigues and Yuri Albuquerque and Rafael Azevedo and Alyson Andrade},
      year={2023},
      eprint={2309.16844},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}