metadata
license: apache-2.0
language:
- multilingual
base_model:
- Qwen/Qwen2-VL-2B-Instruct
tags:
- mmeb
- vidore
- colpali
- multimodal-embedding
Ops-MM-embedding-v1-2B
Ops-MM-embedding-v1-2B is a dense, large-scale multimodal embedding model developed and open-sourced by the Alibaba Cloud OpenSearch-AI team, fine-tuned from Qwen2-VL.
Key Features
Unified Multimodal Embeddings
- Encodes text, images, text-image pairs, visual documents, and videos (by treating video frames as multiple image inputs) into a unified embedding space for cross-modal retrieval.
High Performance on MMEB
- Achieves SOTA results among models of similar scale on MMEB-V2 and MMEB-Image benchmark (until 2025-07-03).
Multilingual Capabilities
- The larger variant (Ops-MM-embedding-v1-7B) achieves SOTA performance among dense models on the ViDoRe-v2 benchmark, demonstrating strong cross-lingual generalization.
Training data
MMEB-train, CC-3M, colpali training set.
Performance
MMEB-V2
| Model | Model Size (B) | Overall | Image-Overall | Video-Overall | Visdoc-Overall |
|---|---|---|---|---|---|
| seed-1.6-embedding | unknown | 71.57 | 77.78 | 55.34 | 74.41 |
| Ops-MM-embedding-v1-7B | 8.29 | 67.79 | 72.72 | 53.76 | 70.91 |
| Ops-MM-embedding-v1-2B | 2.21 | 63.62 | 69.03 | 47.56 | 67.55 |
| VLM2Vec-V2.0-Qwen2VL-2B | 2.21 | 58.39 | 64.85 | 34.85 | 66.34 |
| gme-Qwen2-VL-2B-Instruct | 2.21 | 54.37 | 51.89 | 33.86 | 73.47 |
MMEB-Image
The table below compares performance on MMEB-Image benchmark among models of similar size.
| Model | Model Size (B) | Image-Overall | I-CLS | I-QA | I-RET | I-VG |
|---|---|---|---|---|---|---|
| Ops-MM-embedding-v1-2B | 2.21 | 69.03 | 68.07 | 65.11 | 69.17 | 80.85 |
| B3_Qwen2_2B | 2.21 | 68.1 | 67 | 61.19 | 70.85 | 79.88 |
| LLaVE-2B | 1.95 | 65.2 | 62.1 | 60.2 | 65.2 | 84.9 |
ViDoRe-v2
| Model | Avg | ESG Restaurant Human | MIT Bio | Econ. Macro | ESG Restaurant Synth. | MIT Bio Multi. | Econ Macro Multi. | ESG Restaurant Synth. Multi. |
|---|---|---|---|---|---|---|---|---|
| gme-7B | 59.3 | 65.8 | 64 | 62.9 | 54.3 | 55.1 | 56.2 | 56.7 |
| seed 1.6 embedding | 58.9 | 63.3 | 63.9 | 64.0 | 58.4 | 57.1 | 53.8 | 52.0 |
| Ops-MM-embedding-v1-7B | 60.6 | 66.3 | 58.4 | 67.4 | 60.0 | 54.3 | 60.9 | 56.8 |
| Ops-MM-embedding-v1-2B | 54.4 | 58.6 | 56.0 | 56.4 | 55.8 | 52.9 | 47.9 | 53.4 |
Usage
from ops_mm_embedding_v1 import OpsMMEmbeddingV1, fetch_image
model = OpsMMEmbeddingV1(
"OpenSearch-AI/Ops-MM-embedding-v1-2B",
device="cuda",
attn_implementation="flash_attention_2"
)
t2i_prompt = "Find an image that matches the given text."
texts = [
"The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
"Alibaba office.",
"Alibaba office.",
]
images = [
"https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg",
"https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg",
"https://upload.wikimedia.org/wikipedia/commons/thumb/b/b0/Alibaba_Binjiang_Park.jpg/1024px-Alibaba_Binjiang_Park.jpg"
]
images = [fetch_image(image) for image in images]
# Text and image embedding
text_embeddings = model.get_text_embeddings(texts)
image_embeddings = model.get_image_embeddings(images)
print('Text and image embeddings', (text_embeddings @ image_embeddings.T).tolist())
# Fused Embedding
text_with_image_embeddings = model.get_fused_embeddings(texts=texts, images=images, instruction=t2i_prompt)
print('Text and image embeddings', (text_embeddings @ image_embeddings.T).tolist())
# Multi-image embeddings
multi_images = [
[images[0]],
[images[1], images[2]],
]
multi_image_embeddings = model.get_image_embeddings(multi_images)
print('Multi-image embeddings', (multi_image_embeddings @ multi_image_embeddings.T).tolist())