Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ tags:
|
|
| 16 |
## Introduction
|
| 17 |
We present <a href="https://huggingface.co/Kingsoft-LLM/QZhou-Embedding">QZhou-Embedding</a> (called "Qingzhou Embedding"), a general-purpose contextual text embedding model with exceptional text representation capabilities. Built upon the <a href="https://huggingface.co/Qwen/Qwen2.5-7B-Instruct">Qwen2.5-7B-Instruct</a> foundation model, we designed a unified multi-task framework and developed a data synthesis pipeline leveraging LLM API, effectively improving the diversity and quality of training data, further enhancing the model's generalization and text representation capabilities. Additionally, we employ a two-stage training strategy, comprising initial retrieval-focused training followed by full-task fine-tuning, enabling the embedding model to extend its capabilities based on robust retrieval performance. Our model achieves state-of-the-art results on the MTEB and CMTEB benchmarks, ranking first on both leaderboards(August 27, 2025).
|
| 18 |
|
| 19 |
-
**Latest Updates
|
| 20 |
**1. <span style="font-size: 18px; color:green">Our technical report has now been released. Welcome your feedback！</span>** Link: <a> href="https://arxiv.org/abs/2508.21632">[QZhou-Embedding](https://arxiv.org/abs/2508.21632)</a><br>
|
| 21 |
**2. We have added support for vLLM.**
|
| 22 |
## Basic Features
|
|
|
|
| 16 |
## Introduction
|
| 17 |
We present <a href="https://huggingface.co/Kingsoft-LLM/QZhou-Embedding">QZhou-Embedding</a> (called "Qingzhou Embedding"), a general-purpose contextual text embedding model with exceptional text representation capabilities. Built upon the <a href="https://huggingface.co/Qwen/Qwen2.5-7B-Instruct">Qwen2.5-7B-Instruct</a> foundation model, we designed a unified multi-task framework and developed a data synthesis pipeline leveraging LLM API, effectively improving the diversity and quality of training data, further enhancing the model's generalization and text representation capabilities. Additionally, we employ a two-stage training strategy, comprising initial retrieval-focused training followed by full-task fine-tuning, enabling the embedding model to extend its capabilities based on robust retrieval performance. Our model achieves state-of-the-art results on the MTEB and CMTEB benchmarks, ranking first on both leaderboards(August 27, 2025).
|
| 18 |
|
| 19 |
+
**Latest Updates:**<br>
|
| 20 |
**1. <span style="font-size: 18px; color:green">Our technical report has now been released. Welcome your feedback！</span>** Link: <a> href="https://arxiv.org/abs/2508.21632">[QZhou-Embedding](https://arxiv.org/abs/2508.21632)</a><br>
|
| 21 |
**2. We have added support for vLLM.**
|
| 22 |
## Basic Features
|