---
language: en
license: mit
tags:
- text-summarization
- summarization
- bart
- small-model
- synthetic-data
- tanaos
- artifex
base_model:
- facebook/bart-base
datasets:
- tanaos/synthetic-summarization-dataset-v1
library_name: transformers
task:
  type: summarization
  description: "Abstractive text summarization — condenses long documents into concise, fluent summaries."
---

<p align="center">
    <img src="https://raw.githubusercontent.com/tanaos/.github/master/assets/logo.png" width="250px" alt="Tanaos – Train task specific LLMs without training data, for offline NLP and Text Classification">
</p>

# tanaos-text-summarization-v1: A small but performant text summarization model

This model was created by Tanaos with the [Artifex Python library](https://github.com/tanaos/artifex).

This is an **abstractive text summarization model** based on [facebook/bart-base](https://huggingface.co/facebook/bart-base) and fine-tuned on a synthetic dataset to produce concise, fluent summaries of longer texts. The model uses beam search decoding and is optimized for general-purpose summarization across a variety of domains.

## How to Use

Use this model through the [Artifex library](https://github.com/tanaos/artifex):

install Artifex with

```bash
pip install artifex
```

use the model with

```python
from artifex import Artifex

summarizer = Artifex().text_summarization()

text = """
The Amazon rainforest, often referred to as the "lungs of the Earth", produces about
20% of the world's oxygen and is home to an estimated 10% of all species on the planet.
Deforestation driven by agriculture, logging, and infrastructure development has
destroyed roughly 17% of the forest over the last 50 years, raising urgent concerns
among scientists and policymakers about biodiversity loss and climate change.
"""

summary = summarizer(text)
print(summary)

# >>> "The Amazon rainforest produces 20% of the world's oxygen and harbors 10% of all species, but deforestation has been a major concern."
```

## Model Description

- **Base model:** `facebook/bart-base`
- **Architecture:** `BartForConditionalGeneration` (sequence-to-sequence)
- **Task:** Abstractive text summarization
- **Language:** English
- **Fine-tuning data:** A synthetic, custom dataset of document–summary pairs generated to cover a wide range of topics and writing styles.

## Training Details

This model was trained using the [Artifex Python library](https://github.com/tanaos/artifex)

```bash
pip install artifex
```

by providing the following instructions and generating synthetic training samples:

```python
from artifex import Artifex

summarizer = Artifex().text_summarization()

summarizer.train(
    domain="general",
    num_samples=20000
)
```

## Intended Uses

This model is intended to:
- Condense long documents, articles, or reports into short, readable summaries.
- Be used in applications such as news aggregators, document review tools, and content digests.
- Serve as a general-purpose summarization model applicable across various industries and domains.

Not intended for:
- Highly technical or domain-specific texts where specialized terminology requires domain-adapted models.
- Very short inputs (a few sentences) where summarization adds little value.
- Tasks requiring factual grounding or citations.