xlm roberta large squad2

提供商deepset
分类question-answering
许可证cc-by-4.0
下载量1.1K
星标0

简介

xlm-roberta-large-squad2 是一款基于多语言 RoBERTa 模型并针对 SQuAD 2.0 数据集微调的阅读理解模型。它最大的特点是具备强大的跨语言处理能力，能够直接在多种语言的文本中精准提取答案。与通用 LLM 不同，它专注于“抽取式问答”，即从给定文章中截取原句作为答案，且能识别出问题在文中无解的情况，有效降低了幻觉。对于需要构建知识库问答、自动化文档分析的开发者来说，它是一个轻量且高效的专项工具，上手难度低，可直接部署在本地服务器，无需依赖昂贵的 API。

核心亮点

  • 支持多语言，无需翻译即可直接进行跨语言问答
  • 专注抽取式 QA，答案精准且无幻觉，可靠性高
  • 支持不可答识别，能判断问题是否在文中存在答案
  • 模型规模适中，适合本地化部署与私有化文档分析

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/xlm-roberta-large-squad2")
tokenizer = AutoTokenizer.from_pretrained("deepset/xlm-roberta-large-squad2")

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/xlm-roberta-large-squad2

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/xlm-roberta-large-squad2 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/xlm-roberta-large-squad2')

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/xlm-roberta-large-squad2

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/xlm-roberta-large-squad2

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/xlm-roberta-large-squad2')
tokenizer = AutoTokenizer.from_pretrained('deepset/xlm-roberta-large-squad2')

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/xlm-roberta-large-squad2

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/xlm-roberta-large-squad2 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/xlm-roberta-large-squad2')

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/xlm-roberta-large-squad2.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/xlm-roberta-large-squad2.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/xlm-roberta-large-squad2')

完整文档

来源: HuggingFace

---
language: multilingual
license: cc-by-4.0
tags:

  • question-answering

datasets:
  • squad_v2

model-index:
  • name: deepset/xlm-roberta-large-squad2

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: 81.8281
name: Exact Match
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzVhZDE2NTg5NmUwOWRkMmI2MGUxYjFlZjIzNmMyNDQ2MDY2MDNhYzE0ZjY5YTkyY2U4ODc3ODFiZjQxZWQ2YSIsInZlcnNpb24iOjF9.f_rN3WPMAdv-OBPz0T7N7lOxYz9f1nEr_P-vwKhi3jNdRKp_JTy18MYR9eyJM2riKHC6_ge-8XwfyrUf51DSDA
- type: f1
value: 84.8886
name: F1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGE5MWJmZGUxMGMwNWFhYzVhZjQwZGEwOWQ4N2Q2Yjg5NzdjNDFiNDhiYTQ1Y2E5ZWJkOTFhYmI1Y2Q2ZGYwOCIsInZlcnNpb24iOjF9.TIdH-tOx3kEMDs5wK1r6iwZqqSjNGlBrpawrsE917j1F3UFJVnQ7wJwaj0OIgmC4iw8OQeLZL56ucBcLApa-AQ
---

Multilingual XLM-RoBERTa large for Extractive QA on various languages

Overview

Language model: xlm-roberta-large Language: Multilingual Downstream-task: Extractive QA Training data: SQuAD 2.0 Eval data: SQuAD dev set - German MLQA - German XQuAD Training run: MLFlow link Code: See an example extractive QA pipeline built with Haystack Infrastructure: 4x Tesla v100

Hyperparameters

code
batch_size = 32
n_epochs = 3
base_LM_model = "xlm-roberta-large"
max_seq_len = 256
learning_rate = 1e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64

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/xlm-roberta-large-squad2")
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/xlm-roberta-large-squad2"


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

Evaluated on the SQuAD 2.0 English dev set with the official eval script.
code
"exact": 79.45759285774446,
  "f1": 83.79259828925511,
  "total": 11873,
  "HasAns_exact": 71.96356275303644,
  "HasAns_f1": 80.6460053117963,
  "HasAns_total": 5928,
  "NoAns_exact": 86.93019343986543,
  "NoAns_f1": 86.93019343986543,
  "NoAns_total": 5945

Evaluated on German MLQA: test-context-de-question-de.json

code
"exact": 49.34691166703564,
"f1": 66.15582561674236,
"total": 4517,

Evaluated on German XQuAD: xquad.de.json

code
"exact": 61.51260504201681,
"f1": 78.80206098332569,
"total": 1190,

Usage

In Haystack

For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in haystack:
python
reader = FARMReader(model_name_or_path="deepset/xlm-roberta-large-squad2")

or 

reader = TransformersReader(model="deepset/xlm-roberta-large-squad2",tokenizer="deepset/xlm-roberta-large-squad2")

In Transformers

python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "deepset/xlm-roberta-large-squad2"


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)

Authors

Branden Chan: [email protected] Timo Möller: [email protected] Malte Pietsch: [email protected] Tanay Soni: [email protected]

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