distilbart cnn 6 6

提供商Xenova
分类summarization
许可证apache-2.0
下载量1.7K
星标0

简介

distilbart-cnn-6-6 是一款轻量级的文本摘要模型，通过对 BART 模型进行知识蒸馏，在保持较强语义理解能力的同时，显著降低了推理延迟和显存占用。它专门在 CNN/Daily Mail 新闻数据集上进行了微调，非常适合需要快速提取长文本核心信息的场景。对于开发者而言，该模型上手门槛极低，尤其在端侧部署或构建轻量级摘要插件时，是替代大型 LLM 以降低成本、提升响应速度的理想选择。

核心亮点

  • 专注长文本摘要，能快速提取关键信息
  • 蒸馏架构带来极速推理，低资源占用
  • 适合端侧部署，降低 API 调用成本
  • Apache-2.0 协议，企业级商用无压力

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("Xenova/distilbart-cnn-6-6")
tokenizer = AutoTokenizer.from_pretrained("Xenova/distilbart-cnn-6-6")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download Xenova/distilbart-cnn-6-6

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download Xenova/distilbart-cnn-6-6 config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('Xenova/distilbart-cnn-6-6')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/Xenova/distilbart-cnn-6-6

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/Xenova/distilbart-cnn-6-6

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('Xenova/distilbart-cnn-6-6')
tokenizer = AutoTokenizer.from_pretrained('Xenova/distilbart-cnn-6-6')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 ModelScope：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model Xenova/distilbart-cnn-6-6

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例） 
modelscope download --model Xenova/distilbart-cnn-6-6 README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

SDK 下载 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('Xenova/distilbart-cnn-6-6')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://www.modelscope.cn/Xenova/distilbart-cnn-6-6.git

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/Xenova/distilbart-cnn-6-6.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 快速开发

下载并安装 ModelScope library

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

模型加载和推理

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'Xenova/distilbart-cnn-6-6')

完整文档

来源: HuggingFace

---
base_model: sshleifer/distilbart-cnn-6-6
library_name: transformers.js
license: apache-2.0
pipeline_tag: summarization
---

https://huggingface.co/sshleifer/distilbart-cnn-6-6 with ONNX weights to be compatible with Transformers.js.

Usage (Transformers.js)

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

bash
npm i @huggingface/transformers

Example: Summarization.

js
import { pipeline } from '@huggingface/transformers';

const generator = await pipeline('summarization', 'Xenova/distilbart-cnn-6-6');
const text = 'The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, ' +
  'and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. ' +
  'During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest ' +
  'man-made structure in the world, a title it held for 41 years until the Chrysler Building in New ' +
  'York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to ' +
  'the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the ' +
  'Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second ' +
  'tallest free-standing structure in France after the Millau Viaduct.';
const output = await generator(text, {
  max_new_tokens: 100,
});

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

查看官方来源