Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Salesforce
/
instructblip-vicuna-7b
like
86
Follow
Salesforce
895
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
main
instructblip-vicuna-7b
/
added_tokens.json
xurantju
Update model for latest `transformers` changes (
#14
)
9e55477
verified
about 2 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
61 Bytes
{
"<image>"
:
32001
,
"<video>"
:
32002
,
"[PAD]"
:
32000
}