Update README.md
Browse files
README.md
CHANGED
|
@@ -5,9 +5,15 @@ base_model:
|
|
| 5 |
pipeline_tag: text-ranking
|
| 6 |
---
|
| 7 |
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
-
|
| 11 |
|
| 12 |
`Lychee-rerank` is the latest generalist text embedding model based on the `Qwen2.5` model. It is suitable for reranking of various text retrieval tasks, and supports multiple languages of `Qwen2.5`.
|
| 13 |
`Lychee-rerank` is jointly developed by the NLP Team of Harbin Institute of Technology, Shenzhen and is built based on an innovative multi-stage training framework (warm-up, task-learning, model merging, annealing).
|
|
|
|
| 5 |
pipeline_tag: text-ranking
|
| 6 |
---
|
| 7 |
|
| 8 |
+
<a href="https://github.com/vec-ai/lychee-embed">
|
| 9 |
+
<img src="https://img.shields.io/badge/GitHub-%23121011.svg?logo=github&logoColor=white">
|
| 10 |
+
</a>
|
| 11 |
+
<a href="https://openreview.net/pdf?id=NC6G1KCxlt">
|
| 12 |
+
<img src="https://img.shields.io/badge/Paper-Openreview-red">
|
| 13 |
+
</a>
|
| 14 |
+
|
| 15 |
|
| 16 |
+
# Lychee Rerank
|
| 17 |
|
| 18 |
`Lychee-rerank` is the latest generalist text embedding model based on the `Qwen2.5` model. It is suitable for reranking of various text retrieval tasks, and supports multiple languages of `Qwen2.5`.
|
| 19 |
`Lychee-rerank` is jointly developed by the NLP Team of Harbin Institute of Technology, Shenzhen and is built based on an innovative multi-stage training framework (warm-up, task-learning, model merging, annealing).
|