bert medium squad2 distilled

提供商deepset
分类question-answering
许可证mit
下载量1.1K
星标0

简介

这是一个基于 BERT-Medium 架构并经过 SQuAD 2.0 数据集蒸馏而来的轻量化问答模型。它在保持较强阅读理解能力的同时，大幅降低了计算资源消耗，解决了原版 BERT 模型推理慢、部署难的痛点。对于开发者而言，它非常适合集成到企业知识库、智能客服等需要快速从文档中提取答案的 RAG（检索增强生成）场景中。相比于 GPT-4 等大模型，它更像是一个高效的“精准提取器”，上手简单，且由于采用了 MIT 协议，商业化部署毫无压力。

核心亮点

  • 专为问答设计，能精准从文本中提取答案
  • 经过模型蒸馏，推理速度快且占用资源低
  • 适配 SQuAD 2.0，支持识别不可回答的问题
  • MIT 开源协议，极大方便企业级商业部署

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("deepset/bert-medium-squad2-distilled")
tokenizer = AutoTokenizer.from_pretrained("deepset/bert-medium-squad2-distilled")

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 deepset/bert-medium-squad2-distilled

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 deepset/bert-medium-squad2-distilled 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('deepset/bert-medium-squad2-distilled')

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/deepset/bert-medium-squad2-distilled

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/deepset/bert-medium-squad2-distilled

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('deepset/bert-medium-squad2-distilled')
tokenizer = AutoTokenizer.from_pretrained('deepset/bert-medium-squad2-distilled')

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 deepset/bert-medium-squad2-distilled

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 deepset/bert-medium-squad2-distilled 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('deepset/bert-medium-squad2-distilled')

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/deepset/bert-medium-squad2-distilled.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/deepset/bert-medium-squad2-distilled.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', 'deepset/bert-medium-squad2-distilled')

完整文档

来源: HuggingFace

---
language: en
license: mit
tags:

  • exbert

datasets:
  • squad_v2

thumbnail: https://thumb.tildacdn.com/tild3433-3637-4830-a533-353833613061/-/resize/720x/-/format/webp/germanquad.jpg
model-index:
  • name: deepset/bert-medium-squad2-distilled

results:
- task:
type: question-answering
name: Question Answering
dataset:
name: squad_v2
type: squad_v2
config: squad_v2
split: validation
metrics:
- type: exact_match
value: 69.8231
name: Exact Match
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmE4MGRkZTVjNmViMGNjYjVhY2E1NzcyOGQ1OWE1MWMzMjY5NWU0MmU0Y2I4OWU4YTU5OWQ5YTI2NWE1NmM0ZSIsInZlcnNpb24iOjF9.tnCJvWzMctTwiQu5yig_owO2ZI1t1MZz1AN2lQy4COAGOzuMovD-74acQvMbxJQoRfNNkIetz2hqYivf1lJKDw
- type: f1
value: 72.9232
name: F1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTMwNzk0ZDRjNGUyMjQyNzc1NzczZmUwMTU2MTM5MGQ3M2NhODlmOTU4ZDI0YjhlNTVjNDA1MGEwM2M1MzIyZSIsInZlcnNpb24iOjF9.eElGmTOXH_qHTNaPwZ-dUJfVz9VMvCutDCof_6UG_625MwctT_j7iVkWcGwed4tUnunuq1BPm-0iRh1RuuB-AQ
---

bert-medium-squad2-distilled for Extractive QA

Overview

Language model: deepset/roberta-base-squad2-distilled Language: English Training data: SQuAD 2.0 training set Eval data: SQuAD 2.0 dev set Infrastructure: 1x V100 GPU Published: Apr 21st, 2021

Details

  • Haystack version 1.x distillation feature was used for training. deepset/bert-large-uncased-whole-word-masking-squad2 was used as the teacher model.

Hyperparameters

code
batch_size = 6
n_epochs = 2
max_seq_len = 384
learning_rate = 3e-5
lr_schedule = LinearWarmup
embeds_dropout_prob = 0.1
temperature = 5
distillation_loss_weight = 1

Usage

In Haystack

Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. To load and run the model with Haystack:
python
# After running pip install haystack-ai "transformers[torch,sentencepiece]"

from haystack import Document
from haystack.components.readers import ExtractiveReader


docs = [
    Document(content="Python is a popular programming language"),
    Document(content="python ist eine beliebte Programmiersprache"),
]


reader = ExtractiveReader(model="deepset/bert-medium-squad2-distilled")
reader.warm_up()


question = "What is a popular programming language?"
result = reader.run(query=question, documents=docs)
{'answers': [ExtractedAnswer(query='What is a popular programming language?', score=0.5740374326705933, data='python', document=Document(id=..., content: '...'), context=None, document_offset=ExtractedAnswer.Span(start=0, end=6),...)]}

For a complete example with an extractive question answering pipeline that scales over many documents, check out the corresponding Haystack tutorial.

In Transformers

python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "deepset/bert-medium-squad2-distilled"


a) Get predictions

nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
    'question': 'Why is model conversion important?',
    'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)

b) Load model & tokenizer

model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

Performance

code
"exact": 68.6431398972458
"f1": 72.7637083790805

Authors

  • Timo Möller: timo.moeller [at] deepset.ai
  • Julian Risch: julian.risch [at] deepset.ai
  • Malte Pietsch: malte.pietsch [at] deepset.ai
  • Michel Bartels: michel.bartels [at] deepset.ai

About us

<div class="grid lg:grid-cols-2 gap-x-4 gap-y-3">
<div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
<img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/deepset-logo-colored.png" class="w-40"/>
</div>
<div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
<img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/haystack-logo-colored.png" class="w-40"/>
</div>
</div>

deepset is the company behind the production-ready open-source AI framework Haystack.

Some of our other work:



Get in touch and join the Haystack community

<p>For more info on Haystack, visit our <strong><a href="https://github.com/deepset-ai/haystack">GitHub</a></strong> repo and <strong><a href="https://docs.haystack.deepset.ai">Documentation</a></strong>.

We also have a <strong><a class="h-7" href="https://haystack.deepset.ai/community">Discord community open to everyone!</a></strong></p>

Twitter | LinkedIn | Discord | GitHub Discussions | Website | YouTube

By the way: we're hiring!

查看官方来源