---
base_model:
- Qwen/Qwen3-0.6B
license: cc
---
<br><br>

<p align="center">
<img src="https://huggingface.co/datasets/jinaai/documentation-images/resolve/main/logo.webp" alt="Jina AI: Your Search Foundation, Supercharged!" width="150px">
</p>

### **jina-embeddings-v5-text-small-clustering**: Clustering-Targeted Embedding Distillation

[Blog](https://picsum.photos/200/300) | [Technical Report](https://picsum.photos/200/300) | [API](https://jina.ai/embeddings)

### Model Overview

`jina-embeddings-v5-text-small-clustering` is a compact, high-performance text embedding model designed for clustering.

It is part of the **jina-embeddings-v5-text** model family, which also includes [jina-embeddings-v5-text-nano](https://huggingface.co/jinaai/jina-embeddings-v5-text-nano), a smaller model for more resource-constrained use cases.

Trained using a novel approach that combines distillation with task-specific contrastive losses, `jina-embeddings-v5-text-small-clustering` outperforms existing state-of-the-art models of similar size across diverse embedding benchmarks.

| Feature | Value |
| --- | --- |
| Parameters | 677M |
| Supported Tasks | `clustering`|
| Max Sequence Length | 32768 |
| Embedding Dimension | 1024 |
| Matryoshka Dimensions | 32, 64, 128, 256, 512, 768, 1024 |
| Pooling Strategy | Last-token pooling |
| Base Model | Qwen/Qwen3-0.6B-Base |

### Training and Evaluation

For training details and evaluation results, see our [technical report](https://picsum.photos/200/300).

### Usage

<details>
  <summary>Requirements</a></summary>
  
The following Python packages are required:

- `transformers>=4.57.0`
- `torch>=2.8.0`
- `peft>=0.15.2`
  
### Optional / Recommended
- **flash-attention**: Installing [flash-attention](https://github.com/Dao-AILab/flash-attention) is recommended for improved inference speed and efficiency, but not mandatory.
- **sentence-transformers**: If you want to use the model via the `sentence-transformers` interface, install this package as well.

</details>

<details>
  <summary>via <a href="https://github.com/vllm-project/vllm">vLLM</a></summary>

```python
from vllm import LLM

# Initialize model
name = "jinaai/jina-embeddings-v5-text-small-clustering"
model = LLM(model=name, task="embed", dtype="bfloat16")

# Create text prompts
document1 = "Overview of climate change impacts on coastal cities"
document1_prompt = f"Document: {document1}"

document2 = "The impacts of climate change on large cities"
document2_prompt = f"Document: {document2}"

# Encode all prompts
prompts = [document1_prompt, document2_prompt]
outputs = model.encode(prompts, pooling_task="embed")


embed_document1 = outputs[0].outputs.data
embed_document2 = outputs[1].outputs.data
```

</details>

<details>
  <summary> via <a href="https://github.com/ggml-org/llama.cpp">llama.cpp (GGUF)</a></summary>
After installing <a href="https://github.com/ggml-org/llama.cpp">llama.cpp</a> one can run llama-server to host the embedding model as OpenAI API compatible HTTP server. As an example for using text-matching with F16, you can do:

```sh
llama-server -hf jinaai/jina-embeddings-v5-text-small-clustering:F16 --embedding --pooling last -ub 32768
```

</details>

### License

The model is licensed under CC BY-NC 4.0. For commercial use, please [contact us](link).


### Citation

If you find `jina-embeddings-v5-text-small-clustering` useful in your research, please cite the following paper:

[TODO]