Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,7 @@ tags:
|
|
| 12 |
|
| 13 |
# Lychee Embed
|
| 14 |
|
|
|
|
| 15 |
|
| 16 |
`Lychee-embed` is the latest generalist text embedding model developed based on the `Qwen2.5` basic model. It is suitable for text retrieval (semantic correlation), text similarity and other downstream tasks, and supports multiple languages of `Qwen2.5`.
|
| 17 |
`Lychee-embed` 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).
|
|
|
|
| 12 |
|
| 13 |
# Lychee Embed
|
| 14 |
|
| 15 |
+
[Github](https://github.com/vec-ai/lychee-embed) | [Paper](https://openreview.net/pdf?id=NC6G1KCxlt)
|
| 16 |
|
| 17 |
`Lychee-embed` is the latest generalist text embedding model developed based on the `Qwen2.5` basic model. It is suitable for text retrieval (semantic correlation), text similarity and other downstream tasks, and supports multiple languages of `Qwen2.5`.
|
| 18 |
`Lychee-embed` 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).
|