Official model collection for the paper "TokenPacker: Efficient Visual Projector for Multimodal LLM"
LI WENTONG
sunshine-lwt
AI & ML interests
Computer Vision, Multimodal AI
Recent Activity
upvoted
a
paper
9 days ago
EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an
Egocentric World?
upvoted
a
paper
18 days ago
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
Organizations
Collections
1
models
12
sunshine-lwt/TokenPacker-HD-13b-16patch-36token
Text Generation
•
Updated
•
15
sunshine-lwt/TokenPacker-HD-13b-16patch-64token
Text Generation
•
Updated
•
20
sunshine-lwt/TokenPacker-HD-13b-16patch-144token
Text Generation
•
Updated
•
18
sunshine-lwt/TokenPacker-HD-13b-9patch-144token
Text Generation
•
Updated
•
15
sunshine-lwt/TokenPacker-HD-7b-9patch-144token
Text Generation
•
Updated
•
25
•
1
sunshine-lwt/TokenPacker-13b-144token
Text Generation
•
Updated
•
13
sunshine-lwt/TokenPacker-7b-144token
Text Generation
•
Updated
•
20
sunshine-lwt/Osprey-Chat-7b
Text Generation
•
Updated
•
18
•
1
sunshine-lwt/Osprey-7b-stage2
Text Generation
•
Updated
•
30
sunshine-lwt/Osprey-7b-Refercocog-finetuning
Text Generation
•
Updated
•
23