Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ccclemenfff
/
AVL
like
0
Visual Question Answering
Transformers
Safetensors
OpenGVLab/VideoChat2-IT
Lin-Chen/ShareGPT4V
liuhaotian/LLaVA-Instruct-150K
English
videollama2_mistral
text-generation
multimodal large language model
large video-language model
arxiv:
2406.07476
arxiv:
2306.02858
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
AVL
/
handler.py
Commit History
fix data form support
614cc6d
ccclemenfff
commited on
Jul 1, 2025
support path input from HF UI
b80570e
ccclemenfff
commited on
Jul 1, 2025
change flash_attention_2 to eager
142339c
ccclemenfff
commited on
Jul 1, 2025
fix: disable flash attention 2 for CLIPVisionModel
723daaf
ccclemenfff
commited on
Jul 1, 2025
Disable Flash Attention for CLIP
e65359a
ccclemenfff
commited on
Jul 1, 2025
Add custom handler and requirements
d4a7de9
ccclemenfff
commited on
Jun 30, 2025
ccclemenfff
commited on
