Hugging Face's logo

chhola14bhatoora
/
screen-understanding-micro-v2

Image-Text-to-Text
Safetensors
idefics3
vision-language
screen-understanding
computer-use-agent
cua
conversational
Model card Files
xet
 Community

Screen Understanding Micro V2

This model is a fine-tuned vision-language model (based on Idefics3 / SmolVLM architecture) trained for desktop screen understanding, UI element localization, and action grounding.

Model Details

  • Architecture: Idefics3ForConditionalGeneration
  • Trained Task: Screen perception, UI bounding box mapping, and grounded action prediction for desktop agents.
  • Weights: SafeTensors format (~489 MB)

Associated Repositories

Downloads last month
23
Safetensors
Model size
0.3B params
Tensor type
BF16
·
Inference Providers NEW
Image-Text-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for chhola14bhatoora/screen-understanding-micro-v2

Base model

HuggingFaceTB/SmolLM2-1.7B
Quantized
HuggingFaceTB/SmolLM2-1.7B-Instruct
Quantized
HuggingFaceTB/SmolVLM-Instruct
Finetuned
(154)
this model