TIGER-Lab/VLM2Vec-LoRA
Text Generation
•
Updated
•
151
•
8
VLM2Vec
The VLM2Vec embedding models.
-
-
TIGER-Lab/VLM2Vec-Full
Text Generation • Updated • 31.1k • 25 -
TIGER-Lab/MMEB-train
Viewer • Updated • 2.14M • 1.75k • 13 -
TIGER-Lab/MMEB-eval
Viewer • Updated • 37k • 6.86k • 10 -
TIGER-Lab/VLM2Vec-LLaVa-Next
Image-Text-to-Text • Updated • 1.11k • 2
TIGER-Lab/VLM2Vec-Qwen2VL-7B
Image-Text-to-Text • Updated • 387 • 3Note The current best version VLM2Vec model.
-
TIGER-Lab/VLM2Vec-Qwen2VL-2B
Image-Text-to-Text • Updated • 1.42k -
Y-J-Ju/MMEB-eval
Viewer • Updated • 37k • 184 -
27
MMEB Leaderboard
📊The massive multimodal embedding benchmark