Qwen2-VL Models with Visual Perception Token or used in training process.
Runpeng Yu
rp-yu
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
13 days ago
VeriThinker: Learning to Verify Makes Reasoning Model Efficient
updated
a model
13 days ago
rp-yu/Dimple-7B
new activity
13 days ago
rp-yu/Dimple-7B:Update paper link in model card
Organizations
Collections
1
spaces
2
models
8
rp-yu/Dimple-7B
Image-Text-to-Text
•
Updated
•
797
•
6
rp-yu/Qwen2-VL-2b-VPT-Det-NoPrompt
Image-Text-to-Text
•
Updated
•
4
rp-yu/Qwen2-VL-7b-VPT-CLIP
Image-Text-to-Text
•
Updated
•
481
rp-yu/Qwen2-VL-2b-VPT-Det
Image-Text-to-Text
•
Updated
•
7
rp-yu/Qwen2-VL-2b-VPT-Det-Alignment
Image-Text-to-Text
•
Updated
•
11
rp-yu/Qwen2-VL-2b-VPT-Seg-Alignment
Image-Text-to-Text
•
Updated
•
10
rp-yu/Qwen2-VL-2b-VPT-Seg
Image-Text-to-Text
•
Updated
•
6
rp-yu/Qwen2-VL-2b-VPT-CLIP
Image-Text-to-Text
•
Updated
•
4
•
1