Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# OpenSearch-AI/Ops-ColQwen3-4B
|
| 2 |
|
| 3 |
**Ops-ColQwen3-4B** is a ColPali-style multimodal embedding model based on the **Qwen3-VL-4B-Instruct** architecture, developed and open-sourced by the Alibaba Cloud OpenSearch-AI team. It maps text queries and visual documents such as images and PDF pages into a unified, aligned **multi-vector embedding space**, enabling highly effective retrieval of visual documents.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- Qwen/Qwen3-VL-4B-Instruct
|
| 5 |
+
pipeline_tag: visual-document-retrieval
|
| 6 |
+
library_name: transformers
|
| 7 |
+
tags:
|
| 8 |
+
- transformers
|
| 9 |
+
- multimodal_embedding
|
| 10 |
+
- embedding
|
| 11 |
+
- colpali
|
| 12 |
+
- multilingual-embedding
|
| 13 |
+
- colqwen3
|
| 14 |
+
---
|
| 15 |
# OpenSearch-AI/Ops-ColQwen3-4B
|
| 16 |
|
| 17 |
**Ops-ColQwen3-4B** is a ColPali-style multimodal embedding model based on the **Qwen3-VL-4B-Instruct** architecture, developed and open-sourced by the Alibaba Cloud OpenSearch-AI team. It maps text queries and visual documents such as images and PDF pages into a unified, aligned **multi-vector embedding space**, enabling highly effective retrieval of visual documents.
|