tokenizer = AutoTokenizer.from_pretrained('roberta-large')
model = AutoModel.from_pretrained('AIDA-UPM/star')

examples = ['My text 1', 'This is another text']

def extract_embeddings(texts):
  encoded_texts = tokenizer(texts)
  with torch.no_grad():
    style_embeddings = model(encoded_texts.input_ids,
                             attention_mask=encoded_texts.attention_mask).pooler_output
  return style_embeddings

print(extract_embeddings(examples))

Citation

@article{Huertas-Tato2023Oct,
	author = {Huertas-Tato, Javier and Martin, Alejandro and Camacho, David},
	title = {{Understanding writing style in social media with a supervised contrastively pre-trained transformer}},
	journal = {arXiv},
	year = {2023},
	month = oct,
	eprint = {2310.11081},
	doi = {10.48550/arXiv.2310.11081}
}