README.md

---
tags:
- ColBERT
- PyLate
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- loss:Distillation
base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
pipeline_tag: sentence-similarity
library_name: PyLate
language: en
license: apache-2.0
---

# BiomedBERT ColBERT

This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext). It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.

## Usage (txtai)

This model can be used to build embeddings databases with [txtai](https://github.com/neuml/txtai) for semantic search and/or as a knowledge source for retrieval augmented generation (RAG).

```python
import txtai

embeddings = txtai.Embeddings(
  path="neuml/biomedbert-base-colbert",
  content=True
)
embeddings.index(documents())

# Run a query
embeddings.search("query to run")
```

Late interaction models excel as reranker pipelines.

```python
from txtai.pipeline import Reranker, Similarity

similarity = Similarity(path="neuml/biomedbert-base-colbert", lateencode=True)
ranker = Reranker(embeddings, similarity)
ranker("query to run")
```

## Usage (PyLate)

Alternatively, the model can be loaded with [PyLate](https://github.com/lightonai/pylate).

```python
from pylate import rank, models

queries = [
    "query A",
    "query B",
]

documents = [
    ["document A", "document B"],
    ["document 1", "document C", "document B"],
]

documents_ids = [
    [1, 2],
    [1, 3, 2],
]

model = models.ColBERT(
    model_name_or_path="neuml/biomedbert-base-colbert",
)

queries_embeddings = model.encode(
    queries,
    is_query=True,
)

documents_embeddings = model.encode(
    documents,
    is_query=False,
)

reranked_documents = rank.rerank(
    documents_ids=documents_ids,
    queries_embeddings=queries_embeddings,
    documents_embeddings=documents_embeddings,
)
```

## Evaluation Results

Performance of these models are compared to previously released models trained on medical literature. The most commonly used small embeddings model is also included for comparison.

The following datasets were used to evaluate model performance.

- [PubMed QA](https://huggingface.co/datasets/qiaojin/PubMedQA)
  - Subset: pqa_labeled, Split: train, Pair: (question, long_answer)
- [PubMed Subset](https://huggingface.co/datasets/awinml/pubmed_abstract_3_1k)
  - Split: test, Pair: (title, text)
- [PubMed Summary](https://huggingface.co/datasets/armanc/scientific_papers)
  - Subset: pubmed, Split: validation, Pair: (article, abstract)

Evaluation results are shown below. The [Pearson correlation coefficient](https://en.wikipedia.org/wiki/Pearson_correlation_coefficient) is used as the evaluation metric.

| Model                                                 | PubMed QA | PubMed Subset | PubMed Summary | Average   |
| ----------------------------------------------------- | --------- | ------------- | -------------- | --------- |
| [all-MiniLM-L6-v2](https://hf.co/sentence-transformers/all-MiniLM-L6-v2) | 90.40  | 95.92 | 94.07 | 93.46     |
| [bioclinical-modernbert-base-embeddings](https://hf.co/neuml/bioclinical-modernbert-base-embeddings) | 92.49 | 97.10 | 97.04     | 95.54 |
| [**biomedbert-base-colbert**](https://hf.co/neuml/biomedbert-base-colbert)  | **94.59** | **97.18** | **96.21**  | **95.99**|
| [biomedbert-base-reranker](https://hf.co/neuml/biomedbert-base-reranker)  | 97.66 | 99.76  | 98.81 | 98.74 |
| [pubmedbert-base-embeddings](https://hf.co/neuml/pubmedbert-base-embeddings)       | 93.27  | 97.00 | 96.58 | 95.62 |
| [pubmedbert-base-embeddings-8M](https://hf.co/neuml/pubmedbert-base-embeddings-8M) | 90.05  | 94.29 | 94.15 | 92.83 |

This is the best performing model we've released that's not a cross-encoder. With [MUVERA encoding](https://arxiv.org/abs/2405.19504), this model can be used to index large datasets for semantic search. It can also be used as a faster re-ranker vs. a cross-encoder model.

## Full Model Architecture

```
ColBERT(
  (0): Transformer({'max_seq_length': 511, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'use_residual': False})
)
```