distilbert base nli mean tokens

提供商sentence-transformers
分类natural-language-inference
许可证apache-2.0
下载量1.9K
星标0

简介

这是一个基于 DistilBERT 蒸馏模型并经过 NLI（自然语言推理）数据集微调的轻量化文本向量化模型。它通过对 Token 向量取平均值的方式，将整段文本转化为一个高质量的定长嵌入向量（Embedding）。对于中国开发者而言，该模型是构建语义搜索、文档聚类或文本相似度比对的理想选择。相比于原版 BERT，它在保持相当精度的情况下，推理速度大幅提升，显存占用极低，非常适合部署在资源受限的边缘端或作为 RAG 架构中的快速检索组件。

核心亮点

  • 轻量化设计，推理速度快且资源占用低
  • 擅长将文本转化为高质量的语义向量
  • 适用于语义相似度计算与文本聚类场景
  • 是构建高效 RAG 检索流水线的理想组件

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("sentence-transformers/distilbert-base-nli-mean-tokens")
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/distilbert-base-nli-mean-tokens")

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 sentence-transformers/distilbert-base-nli-mean-tokens

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 sentence-transformers/distilbert-base-nli-mean-tokens 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('sentence-transformers/distilbert-base-nli-mean-tokens')

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/sentence-transformers/distilbert-base-nli-mean-tokens

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/sentence-transformers/distilbert-base-nli-mean-tokens

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('sentence-transformers/distilbert-base-nli-mean-tokens')
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distilbert-base-nli-mean-tokens')

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 sentence-transformers/distilbert-base-nli-mean-tokens

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 sentence-transformers/distilbert-base-nli-mean-tokens 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('sentence-transformers/distilbert-base-nli-mean-tokens')

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/sentence-transformers/distilbert-base-nli-mean-tokens.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/sentence-transformers/distilbert-base-nli-mean-tokens.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', 'sentence-transformers/distilbert-base-nli-mean-tokens')

完整文档

来源: HuggingFace

---
license: apache-2.0
library_name: sentence-transformers
tags:

  • sentence-transformers

  • feature-extraction

  • sentence-similarity

  • transformers

pipeline_tag: feature-extraction
---

⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: SBERT.net - Pretrained Models

sentence-transformers/distilbert-base-nli-mean-tokens

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

code
pip install -U sentence-transformers

Then you can use the model like this:

python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('sentence-transformers/distilbert-base-nli-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
python
from transformers import AutoTokenizer, AutoModel
import torch

#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


Sentences we want sentence embeddings for

sentences = ['This is an example sentence', 'Each sentence is converted']

Load model from HuggingFace Hub

tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distilbert-base-nli-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/distilbert-base-nli-mean-tokens')

Tokenize sentences

encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

Compute token embeddings

with torch.no_grad():
    model_output = model(**encoded_input)

Perform pooling. In this case, max pooling.

sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

Full Model Architecture

code
SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

Citing & Authors

This model was trained by sentence-transformers.

If you find this model helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks:
``bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``

查看官方来源