bart large mnli
简介
核心亮点
- 无需训练数据，定义标签即可实现零样本分类
- 基于自然语言推理，语义理解能力强于关键词匹配
- 部署简单，完美适配 Hugging Face Transformers 库
- 适用于快速构建文本分拣、意图识别等原型功能
使用方法
# 安装 Hugging Face transformers
pip install transformers torch# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("facebook/bart-large-mnli")
tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-mnli")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：
pip install -U huggingface_hub命令行下载
下载完整模型库
huggingface-cli download facebook/bart-large-mnli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 facebook/bart-large-mnli config.json --local-dir ./dirSDK 下载
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('facebook/bart-large-mnli')Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://huggingface.co/facebook/bart-large-mnli如果您希望跳过 lfs 大文件下载，可以使用如下命令
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/facebook/bart-large-mnli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
pip install -U transformers torch模型加载和推理
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('facebook/bart-large-mnli')
tokenizer = AutoTokenizer.from_pretrained('facebook/bart-large-mnli')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：
pip install modelscope命令行下载
下载完整模型库
modelscope download --model facebook/bart-large-mnli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 facebook/bart-large-mnli README.md --local_dir ./dirSDK 下载
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('facebook/bart-large-mnli')Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://www.modelscope.cn/facebook/bart-large-mnli.git如果您希望跳过 lfs 大文件下载，可以使用如下命令
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/facebook/bart-large-mnli.gitModelScope 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
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
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
p = pipeline('text-generation', 'facebook/bart-large-mnli')完整文档
---
license: mit
thumbnail: https://huggingface.co/front/thumbnails/facebook.png
pipeline_tag: zero-shot-classification
datasets:
- multi_nli
---
bart-large-mnli
This is the checkpoint for bart-large after being trained on the MultiNLI (MNLI) dataset.
Additional information about this model:
- The bart-large model page
NLI-based Zero Shot Text Classification
Yin et al. proposed a method for using pre-trained NLI models as a ready-made zero-shot sequence classifiers. The method works by posing the sequence to be classified as the NLI premise and to construct a hypothesis from each candidate label. For example, if we want to evaluate whether a sequence belongs to the class "politics", we could construct a hypothesis of This text is about politics.. The probabilities for entailment and contradiction are then converted to label probabilities.
This method is surprisingly effective in many cases, particularly when used with larger pre-trained models like BART and Roberta. See this blog post for a more expansive introduction to this and other zero shot methods, and see the code snippets below for examples of using this model for zero-shot classification both with Hugging Face's built-in pipeline and with native Transformers/PyTorch code.
#### With the zero-shot classification pipeline
The model can be loaded with the zero-shot-classification pipeline like so:
from transformers import pipeline
classifier = pipeline("zero-shot-classification",
model="facebook/bart-large-mnli")You can then use this pipeline to classify sequences into any of the class names you specify.
sequence_to_classify = "one day I will see the world"
candidate_labels = ['travel', 'cooking', 'dancing']
classifier(sequence_to_classify, candidate_labels)
#{'labels': ['travel', 'dancing', 'cooking'],
'scores': [0.9938651323318481, 0.0032737774308770895, 0.002861034357920289],
'sequence': 'one day I will see the world'}
If more than one candidate label can be correct, pass multi_label=True to calculate each class independently:
candidate_labels = ['travel', 'cooking', 'dancing', 'exploration']
classifier(sequence_to_classify, candidate_labels, multi_label=True)
#{'labels': ['travel', 'exploration', 'dancing', 'cooking'],
'scores': [0.9945111274719238,
0.9383890628814697,
0.0057061901316046715,
0.0018193122232332826],
'sequence': 'one day I will see the world'}
#### With manual PyTorch
# pose sequence as a NLI premise and label as a hypothesis
from transformers import AutoModelForSequenceClassification, AutoTokenizer
nli_model = AutoModelForSequenceClassification.from_pretrained('facebook/bart-large-mnli')
tokenizer = AutoTokenizer.from_pretrained('facebook/bart-large-mnli')
premise = sequence
hypothesis = f'This example is {label}.'
run through model pre-trained on MNLI
x = tokenizer.encode(premise, hypothesis, return_tensors='pt',
truncation_strategy='only_first')
logits = nli_model(x.to(device))[0]
we throw away "neutral" (dim 1) and take the probability of
"entailment" (2) as the probability of the label being true
entail_contradiction_logits = logits[:,[0,2]]
probs = entail_contradiction_logits.softmax(dim=1)
prob_label_is_true = probs[:,1]