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

This model was created by Tanaos with the Artifex Python library.

This is an abstractive text summarization model based on 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:

install Artifex with

pip install artifex

use the model with

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

pip install artifex

by providing the following instructions and generating synthetic training samples:

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.