SentenceTransformer(
  (0): Transformer({'max_seq_length': 64, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (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})
  (2): Asym(
    (anchor-0): Dense({'in_features': 768, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
    (positive-0): Dense({'in_features': 768, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
  )
)

pip install -U sentence-transformers

import torch
import numpy as np
from tqdm.auto import tqdm
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import batch_to_device, cos_sim

# Load the model
model = SentenceTransformer("TechWolf/JobBERT-v2")

def encode_batch(jobbert_model, texts):
    features = jobbert_model.tokenize(texts)
    features = batch_to_device(features, jobbert_model.device)
    features["text_keys"] = ["anchor"]
    with torch.no_grad():
        out_features = jobbert_model.forward(features)
    return out_features["sentence_embedding"].cpu().numpy()

def encode(jobbert_model, texts, batch_size: int = 8):
    # Sort texts by length and keep track of original indices
    sorted_indices = np.argsort([len(text) for text in texts])
    sorted_texts = [texts[i] for i in sorted_indices]
    
    embeddings = []
    
    # Encode in batches
    for i in tqdm(range(0, len(sorted_texts), batch_size)):
        batch = sorted_texts[i:i+batch_size]
        embeddings.append(encode_batch(jobbert_model, batch))
    
    # Concatenate embeddings and reorder to original indices
    sorted_embeddings = np.concatenate(embeddings)
    original_order = np.argsort(sorted_indices)
    return sorted_embeddings[original_order]

# Example usage
job_titles = [
    'Software Engineer',
    'Senior Software Developer',
    'Product Manager',
    'Data Scientist'
]

# Get embeddings
embeddings = encode(model, job_titles)

# Calculate cosine similarity matrix
similarities = cos_sim(embeddings, embeddings)
print(similarities)

tensor([[1.0000, 0.8723, 0.4821, 0.5447],
        [0.8723, 1.0000, 0.4822, 0.5019],
        [0.4821, 0.4822, 1.0000, 0.4328],
        [0.5447, 0.5019, 0.4328, 1.0000]])

@article{01K47W55SG7ZRKFG431ESRXC35,
  abstract     = {{Labor market analysis relies on extracting insights from job advertisements, which provide valuable yet unstructured information on job titles and corresponding skill requirements. While state-of-the-art methods for skill extraction achieve strong performance, they depend on large language models (LLMs), which are computationally expensive and slow. In this paper, we propose ConTeXT-match, a novel contrastive learning approach with token-level attention that is well-suited for the extreme multi-label classification task of skill classification. ConTeXT-match significantly improves skill extraction efficiency and performance, achieving state-of-the-art results with a lightweight bi-encoder model. To support robust evaluation, we introduce Skill-XL a new benchmark with exhaustive, sentence-level skill annotations that explicitly address the redundancy in the large label space. Finally, we present JobBERT V2, an improved job title normalization model that leverages extracted skills to produce high-quality job title representations. Experiments demonstrate that our models are efficient, accurate, and scalable, making them ideal for large-scale, real-time labor market analysis.}},
  author       = {{Decorte, Jens-Joris and Van Hautte, Jeroen and Develder, Chris and Demeester, Thomas}},
  issn         = {{2169-3536}},
  journal      = {{IEEE ACCESS}},
  keywords     = {{Taxonomy,Contrastive learning,Training,Annotations,Benchmark testing,Training data,Large language models,Computational efficiency,Accuracy,Terminology,Labor market analysis,text encoders,skill extraction,job title normalization}},
  language     = {{eng}},
  pages        = {{133596--133608}},
  title        = {{Efficient text encoders for labor market analysis}},
  url          = {{http://doi.org/10.1109/ACCESS.2025.3589147}},
  volume       = {{13}},
  year         = {{2025}},
}

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}