Update README.md
Browse files
README.md
CHANGED
|
@@ -29,11 +29,12 @@ These models are trained via a **three-stage learning framework** consisting of:
|
|
| 29 |
All stages leverage high-quality data generated through an advanced data-refinement pipeline.
|
| 30 |
DMRetriever achieves **state-of-the-art (SOTA)** performance across six retrieval intents at all model scales.
|
| 31 |
|
|
|
|
| 32 |
<p align="center">
|
| 33 |
<img src="https://huggingface.co/DMIR01/DMRetriever/resolve/main/DMRetriever_workflow.png"
|
| 34 |
alt="DMRetriever Workflow" width="750"/>
|
| 35 |
</p>
|
| 36 |
-
|
| 37 |
|
| 38 |
## 📚 Dataset
|
| 39 |
Training data are publicly available on [DMRetriever_MTT](https://huggingface.co/datasets/DMIR01/DMRetriever_MTT).
|
|
|
|
| 29 |
All stages leverage high-quality data generated through an advanced data-refinement pipeline.
|
| 30 |
DMRetriever achieves **state-of-the-art (SOTA)** performance across six retrieval intents at all model scales.
|
| 31 |
|
| 32 |
+
|
| 33 |
<p align="center">
|
| 34 |
<img src="https://huggingface.co/DMIR01/DMRetriever/resolve/main/DMRetriever_workflow.png"
|
| 35 |
alt="DMRetriever Workflow" width="750"/>
|
| 36 |
</p>
|
| 37 |
+
|
| 38 |
|
| 39 |
## 📚 Dataset
|
| 40 |
Training data are publicly available on [DMRetriever_MTT](https://huggingface.co/datasets/DMIR01/DMRetriever_MTT).
|