zenlm/zen3-embedding-small

Zen3 Embedding Small

Compact Zen3 embedding model for high-throughput retrieval applications.

Overview

Built on Zen MoDE (Mixture of Distilled Experts) architecture with small parameters and 8K context window.

Developed by Hanzo AI and the Zoo Labs Foundation.

Quick Start

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("zenlm/zen3-embedding-small")

sentences = [
    "The weather is lovely today.",
    "It's so sunny outside!",
    "He drove to the stadium.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)

# Compute cosine similarities
similarities = model.similarity(embeddings, embeddings)
print(similarities)

API Access

from openai import OpenAI

client = OpenAI(base_url="https://api.hanzo.ai/v1", api_key="your-api-key")
response = client.embeddings.create(model="zen3-embedding-small", input="Your text here")
print(response.data[0].embedding)

Model Details

Attribute	Value
Parameters	small
Architecture	Zen MoDE
Context	8K tokens
License	Apache 2.0

License

Apache 2.0