TIGER-Lab/VLM2Vec-LoRA
Text Generation
•
Updated
•
34
•
11
VLM2Vec
The VLM2Vec embedding models.
-
-
TIGER-Lab/VLM2Vec-Full
Text Generation • 4B • Updated • 51.1k • 28 -
TIGER-Lab/MMEB-train
Viewer • Updated • 2.14M • 10.7k • 16 -
TIGER-Lab/MMEB-eval
Viewer • Updated • 37k • 3.78k • 11 -
TIGER-Lab/VLM2Vec-LLaVa-Next
Image-to-Text • 8B • Updated • 82 • 1
TIGER-Lab/VLM2Vec-Qwen2VL-7B
Image-to-Text • Updated • 2.91k • 10Note The current best version VLM2Vec model.
-
TIGER-Lab/VLM2Vec-Qwen2VL-2B
Image-to-Text • Updated • 2.33k • 1 -
Y-J-Ju/MMEB-eval
Viewer • Updated • 37k • 232 -
MMEB Leaderboard
📊75The massive multimodal embedding benchmark
-
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
Paper • 2507.04590 • Published • 16 -
VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
Paper • 2410.05160 • Published • 4