Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Amirhossein75
/
VLM-Image-Captioning
like
0
Image-to-Text
Transformers
Safetensors
PEFT
jxie/coco_captions
English
vision-language
image-captioning
SmolVLM
LoRA
QLoRA
COCO
accelerate
arxiv:
2504.05299
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
VLM-Image-Captioning
File size: 68 Bytes
5ed07e6
1
2
3
4
5
{
"image_seq_len"
:
81
,
"processor_class"
:
"Idefics3Processor"
}