All MiniLM L2 V2

🚀 最快的文本嵌入模型：tabularisai/all-MiniLM-L2-v2

本模型是从 sentence-transformers/all-MiniLM-L12-v2 蒸馏而来，与最小的 all-MiniLM-L6-v2 模型相比，推理速度几乎快了 2 倍，同时在 CPU 和 GPU 上都能保持较高的准确性。

🚀 快速开始

本模型可用于文本嵌入和检索增强生成（RAG）等任务，下面将详细介绍其使用方法。

💻 使用示例

基础用法

检索增强生成（RAG）示例

可将此模型用作 RAG 管道中的检索器：

from sentence_transformers import SentenceTransformer, util
import faiss
import numpy as np

# Load embedding model
model = SentenceTransformer("tabularisai/all-MiniLM-L2-v2")

# Your 5 simple documents
documents = [
    "Renewable energy comes from natural sources.",
    "Solar panels convert sunlight into electricity.",
    "Wind turbines harness wind power.",
    "Fossil fuels are non-renewable sources of energy.",
    "Hydropower uses water to generate electricity."
]

# Embed documents
doc_embeddings = model.encode(documents, convert_to_numpy=True)

# Create FAISS index
dim = doc_embeddings.shape[1]
index = faiss.IndexFlatL2(dim)
index.add(doc_embeddings)

# Query
query = "What are the benefits of renewable energy?"
query_embedding = model.encode([query], convert_to_numpy=True)

# Search top 3 similar docs
D, I = index.search(query_embedding, k=3)

# Print results
print("Query:", query)
print("\nTop 3 similar documents:")
for rank, idx in enumerate(I[0]):
    print(f"{rank+1}. {documents[idx]} (score: {D[0][rank]:.4f})")

高级用法

句子嵌入示例

首先安装库：

pip install -U sentence-transformers

然后加载模型并对句子进行编码：

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("tabularisai/all-MiniLM-L2-v2")

sentences = [
    "The weather is lovely today.",
    "It's so sunny outside!",
    "He drove to the stadium.",
]

embeddings = model.encode(sentences)
print(embeddings.shape)  # [3, 384]

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)  # [3, 3]

📄 许可证

本项目采用 Apache-2.0 许可证。