Downloads · 30 days
9
7% of all-time downloads
sft_appdelta_gui_agent
xwk123/sft_appdelta_gui_agent
sft_appdelta_gui_agent is a image-text-to-text model from xwk123. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.
Fine-tuned Qwen3-VL-8B-Instruct checkpoint for mobile GUI agent tasks. The model is trained with Thought + Action + toolcall output format.
All-time downloads
136
Public
Parameters
8.8B
87.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.5 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- other
- Model type
- qwen3_vl
- Access
- Public
- Created
- Jun 22, 2026
- Updated
- Jun 30, 2026
- SHA
- 59e23940
Try a prompt
Base models
Model card
From the Hugging Face model README
sft_appdelta_gui_agent
Fine-tuned Qwen3-VL-8B-Instruct checkpoint for mobile GUI agent tasks. The model is trained with Thought + Action + tool_call output format.
Prompt format
- System: mobile GUI agent prompt with Thought / Action / tool_call
- User:
The user query: {task}. Task progress ... - Coordinates: 0-999 grid
Usage
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
model = Qwen3VLForConditionalGeneration.from_pretrained("xwk123/sft_appdelta_gui_agent")
processor = AutoProcessor.from_pretrained("xwk123/sft_appdelta_gui_agent")
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_vl
- License
- other
- Created
- Jun 22, 2026
- Updated
- Jun 30, 2026