Dingyun-Huang/oe-sbert-embedding

Dingyun-Huang/oe-sroberta-embedding

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

The OE-BERT model is domain adapted from bert-base-uncased over research literature in optoelectronics. The adapted model is then fine-tuned on abstracts and titles of optoelectronics research articles for embedding capabilities.

Model Details

Model Description

• Language(s) (NLP): English
• Adapted from model: bert-base-uncased

Model Sources

• Repository: OptoelectronicsLM-codebase (GitHub)
• Paper: Cost-Efficient Domain-Adaptive Pretraining of Language Models for Optoelectronics Applications

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('Dingyun-Huang/oe-sroberta-embedding')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('Dingyun-Huang/oe-sroberta-embedding')
model = AutoModel.from_pretrained('Dingyun-Huang/oe-sroberta-embedding')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

Evaluation Results

For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Citing & Authors

BibTeX:

@article{doi:10.1021/acs.jcim.4c02029,
  author = {Huang, Dingyun and Cole, Jacqueline M.},
  title = {Cost-Efficient Domain-Adaptive Pretraining of Language Models for Optoelectronics Applications},
  journal = {Journal of Chemical Information and Modeling},
  volume = {65},
  number = {5},
  pages = {2476-2486},
  year = {2025},
  doi = {10.1021/acs.jcim.4c02029},
      note ={PMID: 39933074},
  URL = {
          https://doi.org/10.1021/acs.jcim.4c02029
  },
  eprint = { 
          https://doi.org/10.1021/acs.jcim.4c02029
  }
}