Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
zhangzicheng
/
q-sit
like
0
Image-to-Text
Transformers
Safetensors
llava_onevision
image-text-to-text
Inference Endpoints
arxiv:
2503.09197
License:
mit
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
main
q-sit
/
added_tokens.json
zhangzicheng
Upload folder using huggingface_hub
eba9bb9
verified
3 days ago
raw
Copy download link
history
blame
contribute
delete
Safe
122 Bytes
{
"<image>"
:
151646
,
"<video>"
:
151647
,
"<|endoftext|>"
:
151643
,
"<|im_end|>"
:
151645
,
"<|im_start|>"
:
151644
}