Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
openinterx
/
UGC-VideoCaptioner
like
3
Follow
Memories.ai Research
9
Video-Text-to-Text
Transformers
Safetensors
openinterx/UGC-VideoCap
qwen2_5_omni
text-to-audio
multimodal
video-captioning
audio-visual
ugc
arxiv:
2507.11336
License:
mit
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
UGC-VideoCaptioner
12 GB
2 contributors
History:
9 commits
peiranW
Update README.md
aea6447
verified
5 months ago
.gitattributes
1.68 kB
Upload 2 files
5 months ago
README.md
14.1 kB
Update README.md
5 months ago
added_tokens.json
579 Bytes
Upload 16 files
6 months ago
args.json
20.1 kB
Upload 16 files
6 months ago
benchmark.png
325 kB
xet
Upload 2 files
5 months ago
chat_template.jinja
1.28 kB
Upload 16 files
6 months ago
config.json
15.7 kB
Upload 16 files
6 months ago
generation_config.json
74 Bytes
Upload 16 files
6 months ago
merges.txt
1.67 MB
Upload 16 files
6 months ago
model-00001-of-00003.safetensors
4.99 GB
xet
Upload 16 files
6 months ago
model-00002-of-00003.safetensors
5 GB
xet
Upload 16 files
6 months ago
model-00003-of-00003.safetensors
1.98 GB
xet
Upload 16 files
6 months ago
model.safetensors.index.json
242 kB
Upload 16 files
6 months ago
preprocessor_config.json
667 Bytes
Upload 16 files
6 months ago
special_tokens_map.json
833 Bytes
Upload 16 files
6 months ago
spk_dict.pt
260 kB
xet
Upload 16 files
6 months ago
tiktok_qa_sample.png
857 kB
xet
Upload 2 files
5 months ago
tokenizer.json
11.4 MB
xet
Upload 16 files
6 months ago
tokenizer_config.json
5.16 kB
Upload 16 files
6 months ago
vocab.json
2.78 MB
Upload 16 files
6 months ago
