tomg-group-umd/pixelprose
Viewer
β’
Updated
β’
15.6M
β’
599
β’
161
zi
menglan
Β·
AI & ML interests
None yet
Recent Activity
new activity
about 15 hours ago
Qwen/Qwen3-VL-30B-A3B-Instruct:how to use vllm to speed up inference?
new activity
24 days ago
AIDC-AI/Ovis-Image-7B:Will You Make a Step+CFG Distill Version?
Organizations
None yet
how to use vllm to speed up inference?
#11 opened about 15 hours ago
by
menglan
Will You Make a Step+CFG Distill Version?
1
#3 opened about 1 month ago
by
qpqpqpqpqpqp
possible to train a lora for it to do a certain task and multiple inputs for editing and referneces?
β€οΈ
π
1
4
#4 opened about 1 month ago
by
krigeta
Add comprehensive dataset card for Light-Syn
1
#1 opened about 1 month ago
by
nielsr
Inconsistent Annotation Format and Lower Data Quality in the Editing Part
7
#4 opened 3 months ago
by
Rayment
Request to release task tags (e.g., Spatial Reasoning, Object Counting) used in the paper
2
#6 opened 3 months ago
by
BorisYang326
can put the categories meta info (field) in the json file?
#2 opened 3 months ago
by
menglan
how to download the image parts?
#3 opened 3 months ago
by
menglan
RuntimeError: CUDA error: an illegal memory access was encountered
1
#5 opened 4 months ago
by
menglan
How to only use the text and visual embedding?
1
#2 opened 11 months ago
by
Labmem009
TypeError: chat() got an unexpected keyword argument 'video_path'
10
#2 opened 12 months ago
by
skyernest
Error on get_vision_tower
π
2
2
#3 opened 12 months ago
by
Clip-AI
liked
a
dataset
over 1 year ago