TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials

Model trained from TongUI dataset

Model Details

The base model is Qwen/Qwen2.5-VL-3B-Instruct. We fine-tuned base model by Lora.

Safetensors

Model size

3.75B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Base model

Finetuned

(144)

this model

Quantizations