Hugging Face's logo

ruotian
/
ConClick-8B

Image-Text-to-Text
PEFT
Safetensors
gui-grounding
computer-use
qwen3-vl
lora
conclick
Model card Files
xet
 Community
1
How to use from the
Use from the
PEFT library
from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-VL-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "ruotian/ConClick-8B")

ConClick-8B

Model for ConClick: Element-wise Contrastive Learning Improves GUI Grounding. ConClick trains on target–distractor examples with coordinate supervision, listwise ranking, and pairwise margin losses.

Inference ScreenSpot-Pro MMBench-GUI L2 OSWorld-G
Direct 66.03 86.28 70.20
+ ReClick 72.36 87.28 71.76

Contains the LoRA adapter, selection head, and visual-merger state for Qwen/Qwen3-VL-8B-Instruct. Use the ConClick repository to install dependencies, run inference, evaluate, or train.

Downloads last month
35
Inference Providers NEW
Image-Text-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ruotian/ConClick-8B

Base model

Qwen/Qwen3-VL-8B-Instruct
Adapter
(229)
this model

Dataset used to train ruotian/ConClick-8B