Update README: change license to Apache 2.0 and add base model info
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@ language:
|
|
| 3 |
- en
|
| 4 |
- zh
|
| 5 |
- multilingual
|
| 6 |
-
license:
|
| 7 |
library_name: sentence-transformers
|
| 8 |
tags:
|
| 9 |
- sentence-transformers
|
|
@@ -13,18 +13,21 @@ tags:
|
|
| 13 |
- text-embedding
|
| 14 |
- retrieval
|
| 15 |
pipeline_tag: sentence-similarity
|
|
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# MoD-Embedding
|
| 19 |
|
| 20 |
-
MoD-Embedding is a text embedding model designed for semantic search and retrieval tasks. This model supports multiple languages
|
| 21 |
|
| 22 |
## Model Details
|
| 23 |
|
|
|
|
| 24 |
- **Model Size**: 4B parameters
|
| 25 |
- **Max Sequence Length**: 32,768 tokens
|
| 26 |
- **Embedding Dimension**: 2560
|
| 27 |
- **Languages**: English, Chinese, and multilingual support
|
|
|
|
| 28 |
|
| 29 |
## Usage
|
| 30 |
|
|
@@ -98,9 +101,9 @@ print(f"Similarity: {similarity.item():.4f}")
|
|
| 98 |
|
| 99 |
## License
|
| 100 |
|
| 101 |
-
This model is licensed under [
|
| 102 |
|
| 103 |
-
|
| 104 |
|
| 105 |
## Citation
|
| 106 |
|
|
@@ -108,8 +111,20 @@ If you use this model in your research, please cite:
|
|
| 108 |
|
| 109 |
```bibtex
|
| 110 |
@misc{mod-embedding-2025,
|
| 111 |
-
title={MoD-Embedding: Multilingual Text Embedding Model},
|
|
|
|
| 112 |
year={2025},
|
| 113 |
url={https://huggingface.co/bflhc/MoD-Embedding}
|
| 114 |
}
|
| 115 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
- en
|
| 4 |
- zh
|
| 5 |
- multilingual
|
| 6 |
+
license: apache-2.0
|
| 7 |
library_name: sentence-transformers
|
| 8 |
tags:
|
| 9 |
- sentence-transformers
|
|
|
|
| 13 |
- text-embedding
|
| 14 |
- retrieval
|
| 15 |
pipeline_tag: sentence-similarity
|
| 16 |
+
base_model: Qwen/Qwen3-Embedding-4B
|
| 17 |
---
|
| 18 |
|
| 19 |
# MoD-Embedding
|
| 20 |
|
| 21 |
+
MoD-Embedding is a text embedding model designed for semantic search and retrieval tasks. This model is fine-tuned from [Qwen/Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B) and supports multiple languages, providing high-quality embeddings for various applications.
|
| 22 |
|
| 23 |
## Model Details
|
| 24 |
|
| 25 |
+
- **Base Model**: [Qwen/Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B)
|
| 26 |
- **Model Size**: 4B parameters
|
| 27 |
- **Max Sequence Length**: 32,768 tokens
|
| 28 |
- **Embedding Dimension**: 2560
|
| 29 |
- **Languages**: English, Chinese, and multilingual support
|
| 30 |
+
- **Training Method**: LoRA fine-tuning on RTEB datasets
|
| 31 |
|
| 32 |
## Usage
|
| 33 |
|
|
|
|
| 101 |
|
| 102 |
## License
|
| 103 |
|
| 104 |
+
This model is licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0).
|
| 105 |
|
| 106 |
+
This model is derived from [Qwen/Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B), which is also licensed under Apache License 2.0.
|
| 107 |
|
| 108 |
## Citation
|
| 109 |
|
|
|
|
| 111 |
|
| 112 |
```bibtex
|
| 113 |
@misc{mod-embedding-2025,
|
| 114 |
+
title={MoD-Embedding: A Fine-tuned Multilingual Text Embedding Model},
|
| 115 |
+
author={MoD Team},
|
| 116 |
year={2025},
|
| 117 |
url={https://huggingface.co/bflhc/MoD-Embedding}
|
| 118 |
}
|
| 119 |
```
|
| 120 |
+
|
| 121 |
+
Please also cite the base model:
|
| 122 |
+
|
| 123 |
+
```bibtex
|
| 124 |
+
@article{qwen3embedding,
|
| 125 |
+
title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
|
| 126 |
+
author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
|
| 127 |
+
journal={arXiv preprint arXiv:2506.05176},
|
| 128 |
+
year={2025}
|
| 129 |
+
}
|
| 130 |
+
```
|