Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Salesforce
/
instructblip-vicuna-7b
like
87
Follow
Salesforce
964
Image-Text-to-Text
Transformers
PyTorch
Safetensors
English
instructblip
vision
image-captioning
Inference Endpoints
arxiv:
2305.06500
License:
other
Model card
Files
Files and versions
Community
15
Train
Deploy
Use this model
refs/pr/14
instructblip-vicuna-7b
File size: 61 Bytes
291e8a3
92cb457
4fd0ddb
291e8a3
1
2
3
4
5
6
{
"<image>"
:
32001
,
"<video>"
:
32002
,
"[PAD]"
:
32000
}