Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
### Ops-MM-embedding-v1-7B
|
| 2 |
|
| 3 |
**Ops-MM-embedding-v1-7B** is a dense, large-scale multimodal embedding model developed and open-sourced by the Alibaba Cloud OpenSearch-AI team, fine-tuned from Qwen2-VL.
|
| 4 |
|
| 5 |
-
---
|
| 6 |
|
| 7 |
### **Key Features**
|
| 8 |
|
|
@@ -34,7 +45,6 @@ MMEB-train, CC-3M, colpali training set.
|
|
| 34 |
| VLM2Vec-V2.0-Qwen2VL-2B | 2.21 | 58.39 | 64.85 | 34.85 | 66.34 |
|
| 35 |
| gme-Qwen2-VL-2B-Instruct | 2.21 | 54.37 | 51.89 | 33.86 | 73.47 |
|
| 36 |
|
| 37 |
-
---
|
| 38 |
|
| 39 |
#### MMEB-Image
|
| 40 |
|
|
@@ -49,7 +59,6 @@ The table below compares performance on MMEB-Image benchmark among models of sim
|
|
| 49 |
| LLaVE-7B | 8.03 | 70.3 | 65.7 | 65.4 | 70.9 | 91.9 |
|
| 50 |
| UNITE-Instruct-7B | 8.29 | 70.3 | 68.3 | 65.1 | 71.6 | 84.8 |
|
| 51 |
|
| 52 |
-
---
|
| 53 |
|
| 54 |
#### ViDoRe-v2
|
| 55 |
|
|
@@ -62,7 +71,6 @@ The table below compares performance on MMEB-Image benchmark among models of sim
|
|
| 62 |
|
| 63 |
|
| 64 |
|
| 65 |
-
|
| 66 |
## Usage
|
| 67 |
|
| 68 |
```python
|
|
@@ -106,4 +114,4 @@ multi_images = [
|
|
| 106 |
multi_image_embeddings = model.get_image_embeddings(multi_images)
|
| 107 |
print('Multi-image embeddings', (multi_image_embeddings @ multi_image_embeddings.T).tolist())
|
| 108 |
|
| 109 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- multilingual
|
| 5 |
+
base_model:
|
| 6 |
+
- Qwen/Qwen2-VL-7B-Instruct
|
| 7 |
+
tags:
|
| 8 |
+
- mmeb
|
| 9 |
+
- vidore
|
| 10 |
+
- colpali
|
| 11 |
+
- multimodal-embedding
|
| 12 |
+
---
|
| 13 |
### Ops-MM-embedding-v1-7B
|
| 14 |
|
| 15 |
**Ops-MM-embedding-v1-7B** is a dense, large-scale multimodal embedding model developed and open-sourced by the Alibaba Cloud OpenSearch-AI team, fine-tuned from Qwen2-VL.
|
| 16 |
|
|
|
|
| 17 |
|
| 18 |
### **Key Features**
|
| 19 |
|
|
|
|
| 45 |
| VLM2Vec-V2.0-Qwen2VL-2B | 2.21 | 58.39 | 64.85 | 34.85 | 66.34 |
|
| 46 |
| gme-Qwen2-VL-2B-Instruct | 2.21 | 54.37 | 51.89 | 33.86 | 73.47 |
|
| 47 |
|
|
|
|
| 48 |
|
| 49 |
#### MMEB-Image
|
| 50 |
|
|
|
|
| 59 |
| LLaVE-7B | 8.03 | 70.3 | 65.7 | 65.4 | 70.9 | 91.9 |
|
| 60 |
| UNITE-Instruct-7B | 8.29 | 70.3 | 68.3 | 65.1 | 71.6 | 84.8 |
|
| 61 |
|
|
|
|
| 62 |
|
| 63 |
#### ViDoRe-v2
|
| 64 |
|
|
|
|
| 71 |
|
| 72 |
|
| 73 |
|
|
|
|
| 74 |
## Usage
|
| 75 |
|
| 76 |
```python
|
|
|
|
| 114 |
multi_image_embeddings = model.get_image_embeddings(multi_images)
|
| 115 |
print('Multi-image embeddings', (multi_image_embeddings @ multi_image_embeddings.T).tolist())
|
| 116 |
|
| 117 |
+
```
|