All MiniLM L2 V2

🚀 The Fastest Text Embedding Model: tabularisai/all-MiniLM-L2-v2

This model is distilled from sentence-transformers/all-MiniLM-L12-v2, offering almost 2 times faster inference than the smallest all-MiniLM-L6-v2 model, while maintaining high accuracy on both CPU and GPU.

🚀 Quick Start

This model is distilled from sentence-transformers/all-MiniLM-L12-v2, delivering almost 2 times faster inference in comparasion to the smallest all-MiniLM-L6-v2 model, while maintaining strong accuracy on CPU and GPU.

✨ Features

• Distilled from sentence-transformers/all-MiniLM-L12-v2.
• Offers almost 2 times faster inference than the smallest all-MiniLM-L6-v2 model.
• Maintains strong accuracy on both CPU and GPU.

📦 Installation

Install the library:

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage

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]

Advanced Usage

Use this model as a retriever in a RAG pipeline:

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})")

📄 License

This project is licensed under the Apache-2.0 license.