Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Sony
/
VIRTUE-7B-SCaR
like
2
Follow
Sony
177
Image-Text-to-Text
Transformers
PyTorch
TIGER-Lab/MMEB-train
Sony/SCaR-Train
English
qwen2_vl
Embedding
text-generation-inference
arxiv:
2510.00523
License:
cc-by-nc-4.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
VIRTUE-7B-SCaR
16.6 GB
1 contributor
History:
3 commits
SwyWang
update dataset link
e5280a7
10 days ago
images
first upload
10 days ago
.gitattributes
1.65 kB
first upload
10 days ago
README.md
10.6 kB
update dataset link
10 days ago
config.json
2.58 kB
first upload
10 days ago
generation_config.json
215 Bytes
first upload
10 days ago
preprocessor_config.json
570 Bytes
first upload
10 days ago
pytorch_model-00001-of-00004.bin
4.97 GB
xet
first upload
10 days ago
pytorch_model-00002-of-00004.bin
4.99 GB
xet
first upload
10 days ago
pytorch_model-00003-of-00004.bin
4.93 GB
xet
first upload
10 days ago
pytorch_model-00004-of-00004.bin
1.69 GB
xet
first upload
10 days ago
pytorch_model.bin.index.json
56.5 kB
first upload
10 days ago
sam2_reducer_and_vlm_layer.pth
8.15 MB
xet
first upload
10 days ago
special_tokens_map.json
613 Bytes
first upload
10 days ago
tokenizer.json
11.4 MB
xet
first upload
10 days ago
tokenizer_config.json
3.28 kB
first upload
10 days ago
vocab.json
2.78 MB
first upload
10 days ago