Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
OpenGVLab
/
VideoChat-TPO
like
3
Follow
OpenGVLab
620
Video-Text-to-Text
Transformers
Safetensors
feature-extraction
custom_code
arxiv:
2412.19326
License:
mit
Model card
Files
Files and versions
Community
1
Train
Use this model
d107423
VideoChat-TPO
/
third_party
/
cgdetr
/
cg_detr
3 contributors
History:
1 commit
ynhe
init
16dc4f2
about 2 months ago
__pycache__
init
about 2 months ago
scripts
init
about 2 months ago
__init__.py
Safe
0 Bytes
init
about 2 months ago
attention.py
Safe
20.8 kB
init
about 2 months ago
config.py
16.2 kB
init
about 2 months ago
crossattention.py
Safe
21 kB
init
about 2 months ago
inference.py
18.5 kB
init
about 2 months ago
matcher.py
5.68 kB
init
about 2 months ago
misc.py
Safe
499 Bytes
init
about 2 months ago
model.py
63.9 kB
init
about 2 months ago
position_encoding.py
Safe
4.35 kB
init
about 2 months ago
postprocessing_cg_detr.py
3.85 kB
init
about 2 months ago
span_utils.py
4.04 kB
init
about 2 months ago
start_end_dataset.py
17 kB
init
about 2 months ago
text_encoder.py
Safe
1.78 kB
init
about 2 months ago
train.py
11 kB
init
about 2 months ago
transformer.py
37.7 kB
init
about 2 months ago
