Feature Extraction
Transformers
Safetensors
English
Chinese
qwen3
text-generation
zen
zen-embedding
zenlm
hanzo
embedding
text-embeddings-inference
Instructions to use zenlm/zen-embedding-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zenlm/zen-embedding-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="zenlm/zen-embedding-4B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-embedding-4B") model = AutoModelForCausalLM.from_pretrained("zenlm/zen-embedding-4B") - Notebooks
- Google Colab
- Kaggle
metadata
license: apache-2.0
library_name: transformers
pipeline_tag: feature-extraction
language:
- en
- zh
tags:
- zen
- zen-embedding
- zenlm
- hanzo
- embedding
Zen Embedding 4B
4B-parameter sentence-embedding model for retrieval-augmented generation, semantic search, and dense retrieval. Part of the Zen embedding family.
Hosted via Hanzo gateway
Served at api.hanzo.ai as zen-embedding-4b.
Files
Native HuggingFace safetensors weights, loadable directly with transformers:
from transformers import AutoModel, AutoTokenizer
m = AutoModel.from_pretrained("zenlm/zen-embedding-4B")
t = AutoTokenizer.from_pretrained("zenlm/zen-embedding-4B")
For GGUF / Ollama deployment, see zenlm/zen-embedding-4B-GGUF.