### Install sentence-transformers

Source: https://github.com/fremycompany/biolord-2023/blob/main/README.md

Install the sentence-transformers library using pip. This is required for the simplified usage of the BioLORD-2023 model.

```bash
pip install -U sentence-transformers
```

--------------------------------

### Encode sentences with sentence-transformers

Source: https://github.com/fremycompany/biolord-2023/blob/main/README.md

Use the SentenceTransformer class to load the BioLORD-2023 model and encode a list of sentences into embeddings. This is the simplest way to get sentence embeddings.

```python
from sentence_transformers import SentenceTransformer
sentences = ["Cat scratch injury", "Cat scratch disease", "Bartonellosis"]

model = SentenceTransformer('FremyCompany/BioLORD-2023')
embeddings = model.encode(sentences)
print(embeddings)
```

--------------------------------

### Encode sentences with HuggingFace Transformers

Source: https://github.com/fremycompany/biolord-2023/blob/main/README.md

Load the BioLORD-2023 model and tokenizer using HuggingFace Transformers. Tokenize sentences, compute token embeddings, apply mean pooling, and normalize the resulting sentence embeddings.

```python
# Sentences we want sentence embeddings for
sentences = ["Cat scratch injury", "Cat scratch disease", "Bartonellosis"]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('FremyCompany/BioLORD-2023')
model = AutoModel.from_pretrained('FremyCompany/BioLORD-2023')

# 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
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:")
print(sentence_embeddings)
```

--------------------------------

### Mean Pooling for Sentence Embeddings with HuggingFace Transformers

Source: https://github.com/fremycompany/biolord-2023/blob/main/README.md

A utility function for mean pooling token embeddings, considering the attention mask. This is used to compute sentence embeddings from token embeddings generated by the HuggingFace Transformers model.

```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F

#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)
```

--------------------------------

### Citation for BioLORD-2023 Paper

Source: https://github.com/fremycompany/biolord-2023/blob/main/README.md

When using the BioLORD-2023 model, please cite the accompanying paper using this LaTeX format.

```latex
@article{remy-etal-2023-biolord,
    author = {Remy, François and Demuynck, Kris and Demeester, Thomas},
    title = "{BioLORD-2023: semantic textual representations fusing large language models and clinical knowledge graph insights}",
    journal = {Journal of the American Medical Informatics Association},
    pages = {ocae029},
    year = {2024},
    month = {02},
    issn = {1527-974X},
    doi = {10.1093/jamia/ocae029},
    url = {https://doi.org/10.1093/jamia/ocae029},
    eprint = {https://academic.oup.com/jamia/advance-article-pdf/doi/10.1093/jamia/ocae029/56772025/ocae029.pdf},
}
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.