bge base en v1.5

提供商Xenova
分类feature-extraction
许可证mit
下载量1.4K
星标0

简介

bge-base-en-v1.5 是一款由 BAAI（北京智源人工智能研究院）推出的高性能英文文本向量化模型。它属于特征提取类模型，核心作用是将文本转化为高维向量，从而实现语义搜索、文档聚类或构建 RAG（检索增强生成）系统的知识库。相比于通用 LLM，它更轻量且专注，能够精准捕捉英文语义的相似度。对于开发者而言，该模型上手门槛极低，尤其在结合 LangChain 或 LlamaIndex 等框架时，可作为高效的 Embedding 层，显著提升本地知识库的检索精度。

核心亮点

  • 由智源研究院开发，英文语义检索精度极高
  • 核心用于 RAG 架构中的文档向量化与匹配
  • 轻量化部署，支持快速提取文本特征向量
  • 兼容主流 AI 框架，是构建语义搜索的理想选择

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/bge-base-en-v1.5")
tokenizer = AutoTokenizer.from_pretrained("Xenova/bge-base-en-v1.5")

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/bge-base-en-v1.5

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/bge-base-en-v1.5 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/bge-base-en-v1.5')

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/bge-base-en-v1.5

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/bge-base-en-v1.5

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/bge-base-en-v1.5')
tokenizer = AutoTokenizer.from_pretrained('Xenova/bge-base-en-v1.5')

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/bge-base-en-v1.5

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/bge-base-en-v1.5 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/bge-base-en-v1.5')

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/bge-base-en-v1.5.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/bge-base-en-v1.5.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/bge-base-en-v1.5')

完整文档

来源: HuggingFace

---
base_model: BAAI/bge-base-en-v1.5
library_name: transformers.js
license: mit
---

https://huggingface.co/BAAI/bge-base-en-v1.5 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

You can then use the model to compute embeddings, as follows:

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

// Create a feature-extraction pipeline
const extractor = await pipeline('feature-extraction', 'Xenova/bge-base-en-v1.5');


// Compute sentence embeddings
const texts = ['Hello world.', 'Example sentence.'];
const embeddings = await extractor(texts, { pooling: 'mean', normalize: true });
console.log(embeddings);
// Tensor {
//   dims: [ 2, 768 ],
//   type: 'float32',
//   data: Float32Array(1536) [ 0.019079938530921936, 0.041718777269124985, ... ],
//   size: 1536
// }


console.log(embeddings.tolist()); // Convert embeddings to a JavaScript list
// [
//   [ 0.019079938530921936, 0.041718777269124985, 0.037672195583581924, ... ],
//   [ 0.020936904475092888, 0.020080938935279846, -0.00787576474249363, ... ]
// ]

You can also use the model for retrieval. For example:

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


// Create a feature-extraction pipeline
const extractor = await pipeline('feature-extraction', 'Xenova/bge-base-en-v1.5');


// List of documents you want to embed
const texts = [
    'Hello world.',
    'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.',
    'I love pandas so much!',
];


// Compute sentence embeddings
const embeddings = await extractor(texts, { pooling: 'mean', normalize: true });


// Prepend recommended query instruction for retrieval.
const query_prefix = 'Represent this sentence for searching relevant passages: '
const query = query_prefix + 'What is a panda?';
const query_embeddings = await extractor(query, { pooling: 'mean', normalize: true });


// Sort by cosine similarity score
const scores = embeddings.tolist().map(
    (embedding, i) => ({
        id: i,
        score: cos_sim(query_embeddings.data, embedding),
        text: texts[i],
    })
).sort((a, b) => b.score - a.score);
console.log(scores);
// [
//   { id: 1, score: 0.7787772374597298, text: 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.' },
//   { id: 2, score: 0.7071589521880506, text: 'I love pandas so much!' },
//   { id: 0, score: 0.4252782730390429, text: 'Hello world.' }
// ]

---

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