Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
Paper
•
2412.05271
•
Published
•
121
•
5
Zhe Chen
czczup
AI & ML interests
multimodal large language model, vision foundation model
Recent Activity
updated
a model
about 4 hours ago
OpenGVLab/InternVL
liked
a model
about 9 hours ago
czczup/textnet-small
liked
a model
about 9 hours ago
czczup/textnet-tiny
Organizations
czczup's activity
Model weights size clarification ?
2
#2 opened 4 days ago
by
nfunctor
Finetune support
1
#3 opened 14 days ago
by
404dreamer
Adding `safetensors` variant of this model
#2 opened 3 days ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened 5 days ago
by
SFconvertbot
Update config for T4 Ampere devices
#15 opened 4 months ago
by
jeanflop
Adding `safetensors` variant of this model
#1 opened 6 days ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened 6 days ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened 5 days ago
by
SFconvertbot
Request AWQ quantized version
2
#1 opened 15 days ago
by
yourModel
What size is the model used in the demo page?
1
#2 opened 11 days ago
by
WOO-SEOK
use internVL2.5 78b in a modular fashion
1
#1 opened 19 days ago
by
Walley
Image resolutions that will work well?
1
#2 opened 18 days ago
by
stmacdonell
Adding `safetensors` variant of this model
#1 opened 6 days ago
by
SFconvertbot
How should I extract attention maps? Can you provide a specific example?
1
#21 opened about 1 month ago
by
whopeople
部署好的vl1.5多模态大模型，目前只接受图片或文本输入吗？是否接受PDF/ppt/excel等文件输入？这种怎么实现
1
#26 opened 20 days ago
by
wqw0806
CUDA error: device-side assert triggered
1
#10 opened 2 months ago
by
67L1
it run on colab t4
1
#1 opened 16 days ago
by
rakmik
some question about dataset format
1
#19 opened 2 months ago
by
MasoShizuka
How to fine -tune this model
1
#22 opened 22 days ago
by
Shreeyut
commented
a
paper
16 days ago