scincl

from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer("malteos/scincl")

# Concatenate the title and abstract with the [SEP] token
papers = [
    "BERT [SEP] We introduce a new language representation model called BERT",
    "Attention is all you need [SEP] The dominant sequence transduction models are based on complex recurrent or convolutional neural networks",
]
# Inference
embeddings = model.encode(papers)

# Compute the (cosine) similarity between embeddings
similarity = model.similarity(embeddings[0], embeddings[1])
print(similarity.item())
# => 0.8440517783164978

from transformers import AutoTokenizer, AutoModel

# load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('malteos/scincl')
model = AutoModel.from_pretrained('malteos/scincl')

papers = [{'title': 'BERT', 'abstract': 'We introduce a new language representation model called BERT'},
          {'title': 'Attention is all you need', 'abstract': ' The dominant sequence transduction models are based on complex recurrent or convolutional neural networks'}]

# concatenate title and abstract with [SEP] token
title_abs = [d['title'] + tokenizer.sep_token + (d.get('abstract') or '') for d in papers]

# preprocess the input
inputs = tokenizer(title_abs, padding=True, truncation=True, return_tensors="pt", max_length=512)

# inference
result = model(**inputs)

# take the first token ([CLS] token) in the batch as the embedding
embeddings = result.last_hidden_state[:, 0, :]

# calculate the similarity
embeddings = torch.nn.functional.normalize(embeddings, p=2, dim=1)
similarity = (embeddings[0] @ embeddings[1].T)
print(similarity.item())
# => 0.8440518379211426