distilbart xsum 12 6

Providersshleifer
Categorysummarization
Licenseapache-2.0
Downloads14
Stars0

Overview

DistilBART-xsum-12-6 is a compressed version of the BART architecture specifically fine-tuned for extreme summarization. Unlike general-purpose models that extract sentences, this model is optimized for abstractive summarization, meaning it generates concise, one-sentence summaries that capture the core essence of a document. For developers, this model offers a strategic balance between latency and performance; it provides a significantly smaller memory footprint and faster inference speeds than the full BART-large model while retaining high semantic accuracy. It is ideal for integrating into news aggregators, notification systems, or any pipeline requiring rapid, high-density text condensation without the overhead of a massive LLM.

Highlights

  • Optimized for fast, abstractive one-sentence summarization
  • Reduced latency and memory usage via distillation
  • Apache-2.0 license for flexible commercial deployment
  • Efficient alternative to full-scale BART models

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("sshleifer/distilbart-xsum-12-6")
tokenizer = AutoTokenizer.from_pretrained("sshleifer/distilbart-xsum-12-6")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download sshleifer/distilbart-xsum-12-6

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download sshleifer/distilbart-xsum-12-6 config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('sshleifer/distilbart-xsum-12-6')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/sshleifer/distilbart-xsum-12-6

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/sshleifer/distilbart-xsum-12-6

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('sshleifer/distilbart-xsum-12-6')
tokenizer = AutoTokenizer.from_pretrained('sshleifer/distilbart-xsum-12-6')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance 
pip install modelscope

CLI Download

Download the full repository

Download the full repository 
modelscope download --model sshleifer/distilbart-xsum-12-6

Download a single file to a local folder (e.g. README.md into ./dir)

Download a single file to a local folder (e.g. README.md into ./dir) 
modelscope download --model sshleifer/distilbart-xsum-12-6 README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('sshleifer/distilbart-xsum-12-6')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/sshleifer/distilbart-xsum-12-6.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/sshleifer/distilbart-xsum-12-6.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

Install the ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

Load the model and run inference 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'sshleifer/distilbart-xsum-12-6')

Full Documentation

来源: HuggingFace

---
language: en
tags:

  • summarization

license: apache-2.0
datasets:
  • cnn_dailymail

  • xsum

thumbnail: https://huggingface.co/front/thumbnails/distilbart_medium.png
---

Usage

This checkpoint should be loaded into BartForConditionalGeneration.from_pretrained. See the BART docs for more information.

Metrics for DistilBART models

| Model Name | MM Params | Inference Time (MS) | Speedup | Rouge 2 | Rouge-L |
|:---------------------------|------------:|----------------------:|----------:|----------:|----------:|
| distilbart-xsum-12-1 | 222 | 90 | 2.54 | 18.31 | 33.37 |
| distilbart-xsum-6-6 | 230 | 132 | 1.73 | 20.92 | 35.73 |
| distilbart-xsum-12-3 | 255 | 106 | 2.16 | 21.37 | 36.39 |
| distilbart-xsum-9-6 | 268 | 136 | 1.68 | 21.72 | 36.61 |
| bart-large-xsum (baseline) | 406 | 229 | 1 | 21.85 | 36.50 |
| distilbart-xsum-12-6 | 306 | 137 | 1.68 | 22.12 | 36.99 |
| bart-large-cnn (baseline) | 406 | 381 | 1 | 21.06 | 30.63 |
| distilbart-12-3-cnn | 255 | 214 | 1.78 | 20.57 | 30.00 |
| distilbart-12-6-cnn | 306 | 307 | 1.24 | 21.26 | 30.59 |
| distilbart-6-6-cnn | 230 | 182 | 2.09 | 20.17 | 29.70 |

View official source
Join our Telegram