Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ColorfulAI
/
videollamb-llava-1.5-7b
like
4
Video-Text-to-Text
Transformers
Safetensors
liuhaotian/LLaVA-Instruct-150K
OpenGVLab/VideoChat2-IT
English
llava_llama
Inference Endpoints
arxiv:
2409.01071
License:
mit
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
Edit model card
Paper:
https://huggingface.co/papers/2409.01071
Downloads last month
59
Safetensors
Model size
7.48B params
Tensor type
BF16
·
Inference API
Video-Text-to-Text
Inference API (serverless) does not yet support transformers models for this pipeline type.
Datasets used to train
ColorfulAI/videollamb-llava-1.5-7b
liuhaotian/LLaVA-Instruct-150K
Preview
•
Updated
Jan 3
•
975
•
443
OpenGVLab/VideoChat2-IT
Viewer
•
Updated
Jun 29
•
1.82M
•
76
•
38