Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
internlm
/
CapRL-Qwen3VL-4B
like
8
Follow
Intern Large Models
923
Image-Text-to-Text
Transformers
Safetensors
internlm/CapRL-2M
English
qwen3_vl
image-to-text
multimodal
image caption
captioning
conversational
arxiv:
2509.22647
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
CapRL-Qwen3VL-4B
/
assets
16.7 MB
1 contributor
History:
1 commit
yuhangzang
Add files using upload-large-folder tool
1bcc7ff
verified
about 1 month ago
comparison.png
3.41 MB
xet
Add files using upload-large-folder tool
about 1 month ago
info_caprl.png
3.9 MB
xet
Add files using upload-large-folder tool
about 1 month ago
info_caprl2.png
2.85 MB
xet
Add files using upload-large-folder tool
about 1 month ago
natural_caprl.png
4.21 MB
xet
Add files using upload-large-folder tool
about 1 month ago
performance.png
147 kB
xet
Add files using upload-large-folder tool
about 1 month ago
performance_caprl2_0.png
136 kB
xet
Add files using upload-large-folder tool
about 1 month ago
performance_update.png
140 kB
xet
Add files using upload-large-folder tool
about 1 month ago
teaser.png
1.88 MB
xet
Add files using upload-large-folder tool
about 1 month ago
