TIGER-Lab/Mantis-8B-Idefics2
Image-Text-to-Text
•
Updated
•
492
•
11
Mantis
Mantis model family optimized for multi-image reasoning with interleaved text/image format
Note Current SoTA Mantis variant
-
TIGER-Lab/Mantis-8B-clip-llama3
Image-Text-to-Text • Updated • 534 • 1
TIGER-Lab/Mantis-8B-siglip-llama3
Image-Text-to-Text • Updated • 4.13k • 31Note Current SoTA Mantis variant without multi-image pre-training
TIGER-Lab/Mantis-Instruct
Viewer • Updated • 999k • 1.46k • 30Note Our training dataset
TIGER-Lab/Mantis-Eval
Viewer • Updated • 217 • 1.5k • 6Note Curated evaluation benchmark for multi-image scenarios
-
MANTIS: Interleaved Multi-Image Instruction Tuning
Paper • 2405.01483 • Published • 6 -
Running on Zero24👁
Mantis
Multimodal Language Model
-
TIGER-Lab/Mantis-llava-7b
Image-Text-to-Text • Updated • 12 • 15 -
TIGER-Lab/Mantis-bakllava-7b
Image-Text-to-Text • Updated • 24 • 5 -
TIGER-Lab/Mantis-8B-Fuyu
Text Generation • Updated • 323 • 4 -
TIGER-Lab/OBELICS-100K
Viewer • Updated • 212k • 33 • 2