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
20 days ago
VeriThinker: Learning to Verify Makes Reasoning Model Efficient
updated
a model
21 days ago
rp-yu/Dimple-7B
new activity
21 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
•
1.16k
•
6
rp-yu/Qwen2-VL-2b-VPT-Det-NoPrompt
Image-Text-to-Text
•
Updated
•
9
rp-yu/Qwen2-VL-7b-VPT-CLIP
Image-Text-to-Text
•
Updated
•
13
rp-yu/Qwen2-VL-2b-VPT-Det
Image-Text-to-Text
•
Updated
•
10
rp-yu/Qwen2-VL-2b-VPT-Det-Alignment
Image-Text-to-Text
•
Updated
•
18
rp-yu/Qwen2-VL-2b-VPT-Seg-Alignment
Image-Text-to-Text
•
Updated
•
14
rp-yu/Qwen2-VL-2b-VPT-Seg
Image-Text-to-Text
•
Updated
•
9
rp-yu/Qwen2-VL-2b-VPT-CLIP
Image-Text-to-Text
•
Updated
•
20
•
1