clarify VLM model used?
#1
by
davanstrien
HF staff
- opened
README.md
CHANGED
|
@@ -8,7 +8,7 @@ tags:
|
|
| 8 |
- colpali
|
| 9 |
- vidore
|
| 10 |
---
|
| 11 |
-
# ColQwen2: Visual Retriever based on
|
| 12 |
|
| 13 |
ColQwen is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features.
|
| 14 |
It is a [Qwen2-VL-2B](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) extension that generates [ColBERT](https://arxiv.org/abs/2004.12832)- style multi-vector representations of text and images.
|
|
|
|
| 8 |
- colpali
|
| 9 |
- vidore
|
| 10 |
---
|
| 11 |
+
# ColQwen2: Visual Retriever based on Qwen2-VL-2B-Instruct with ColBERT strategy
|
| 12 |
|
| 13 |
ColQwen is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features.
|
| 14 |
It is a [Qwen2-VL-2B](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) extension that generates [ColBERT](https://arxiv.org/abs/2004.12832)- style multi-vector representations of text and images.
|