---
base_model:
- Qwen/Qwen2.5-Coder-0.5B
---

<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>

<p align="center">
<b>The code embedding model trained by <a href="https://jina.ai/"><b>Jina AI</b></a>.</b>
</p>

# Jina Embeddings c1: A Small but Performant Code Embedding Model

## Intended Usage & Model Info
`jina-embeddings-c1` is an embedding model for code retrieval. 
The model supports various types of code retrieval (text-to-code, code-to-code, code-to-text, code-to-completion) and technical question answering across 15+ programming languages. 


Built on [Qwen/Qwen2.5-Coder-0.5B](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B), `jina-embeddings-c1` features:

- **Multilingual support** (15+ programming languages) and compatibility with a wide range of domains, including web development, software development, machine learning, data science, and educational coding problems.
- **Task-specific instruction prefixes** for NL2Code, Code2Code, Code2NL, Code2Completion, and Technical QA, which can be selected at inference time.
- **Flexible embedding size**: dense embeddings are 896-dimensional by default but can be truncated to as low as 64 with minimal performance loss.


Summary of features:

| Feature   | Jina Embeddings C1   |
|------------|------------|
| Base Model | Qwen2.5-Coder-0.5B |
| Supported Tasks | `nl2code`, `code2code`, `code2nl`, `code2completion`, `qa` |
| Model DType | BFloat 16 |
| Max Sequence Length | 32768 |
| Embedding Vector Dimension | 896 |
| Matryoshka dimensions | 64, 128, 256, 512, 896 |
| Pooling Strategy | Last-token pooling |
| Attention Mechanism | FlashAttention2 |

## Usage

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

- `transformers>=4.53.0`
- `torch>=2.7.1`
  
### 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.
</details>

<details>
  <summary>via <a href="https://huggingface.co/docs/transformers/en/index">transformers</a></summary>

```python
# !pip install transformers>=4.53.0 torch>=2.7.1

from transformers import AutoModel
import torch

# Initialize the model
model = AutoModel.from_pretrained("jinaai/jina-embeddings-c1-0.5B", trust_remote_code=True)
model.to("cuda")

# Configure truncate_dim, max_length, batch_size in the encode function if needed

# Encode query
query_embeddings = model.encode(
    ["print hello world in python"],
    task="nl2code",
    prompt_name="query",
)

# Encode passage
passage_embeddings = model.encode(
    ["print('Hello World!')"],
    task="nl2code",
    prompt_name="passage",
)
```
</details>

## Training & Evaluation

Please refer to our technical report of jina-embeddings-c1 for training details and benchmarks.

## Contact

Join our [Discord community](https://discord.jina.ai) and chat with other community members about ideas.