Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
TIGER-Lab
/
VLM2Vec-Qwen2VL-7B
like
10
Follow
TIGER-Lab
462
Image-to-Text
Transformers
PyTorch
TIGER-Lab/MMEB-train
English
qwen2_vl
text-generation-inference
arxiv:
2410.05160
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
4
Deploy
Use this model
main
VLM2Vec-Qwen2VL-7B
File size: 66 Bytes
d77bcea
1
2
3
4
5
{
"acc"
:
0.828
,
"num_correct"
:
828
,
"num_pred"
:
1000
}