GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
drunksu
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
drunksu
Model Tree
Qwen/Qwen2.5-VL-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Property | Value |
|---|---|
| Base model | Qwen/Qwen2.5-VL-3B-Instruct |
| Parameters | 3B (bfloat16, ~7 GB) |
| Training | RL alignment |
| Evaluation | SwipeBench |
| Input | GUI screenshots / screen videos + instruction |
| Output | Human-like swipe action (trajectory) |
| Hardware | NVIDIA GPUs (see paper for details) |
python
import torchfrom transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorrepo_id = "drunksu/GUISwiper"model = Qwen2_5_VLForConditionalGeneration.from_pretrained(repo_id,torch_dtype=torch.bfloat16,device_map="auto",)processor = AutoProcessor.from_pretrained(repo_id)# image (GUI screenshot) + instruction -> swipe trajectory# (follow the prompt format in the SwipeGen repo for the full inference pipeline)image = load_your_gui_screenshot() # PIL.Imagemessages = [{"role": "user", "content": [{"type": "image", "image": image},{"type": "text", "text": "Describe the swipe to perform here."},]}]text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device)output = model.generate(**inputs, max_new_tokens=256)print(processor.batch_decode(output, skip_special_tokens=True)[0])
Requires
transformers >= 4.49.0. See the SwipeGen GitHub repo for the complete inference and evaluation pipeline.
python
from huggingface_hub import hf_hub_downloadpath = hf_hub_download("drunksu/GUISwiper", "model-00001-of-00002.safetensors")
bibtex
@misc{swipegen2026,title = {SwipeGen: Bridging the Execution Gap in GUI Agents via Human-like Swipe Synthesis},author = {SwipeGen Team},journal = {arXiv preprint arXiv:2601.18305},year = {2026},note = {Code and models: \url{https://github.com/TSKGHS17/SwipeGen}}}
If you use GUISwiper, please also reference the official repository: https://github.com/TSKGHS17/SwipeGen.
The model weights are released under Apache-2.0, consistent with the base model
Qwen2.5-VL-3B-Instruct. Users should comply with the original license terms of Qwen2.5-VL
and use the model responsibly; outputs are generated by AI and may contain errors.