GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ruotian
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
ruotian
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This release contains the LoRA adapter, auxiliary selection head, and the visual-merger state used by the selected checkpoint. The inference code loads them on Qwen/Qwen3-VL-8B-Instruct at revision 0c351dd01ed87e9c1b53cbc748cba10e6187ff3b. The visual encoder and merger remain frozen during training. This is one directly trained checkpoint, not an average of checkpoints.
See SelectGround for installation, the exact training recipe, direct inference, LCR, and evaluation of all three benchmarks.
bash
python infer.py --model ruotian/SelectGround-8B --image screenshot.png --instruction "Click the Save button"python infer.py --model ruotian/SelectGround-8B --image screenshot.png --instruction "Click the Save button" --lcr
Output point is in original-image pixels. normalized_point uses 0–1000 coordinates. Generation is greedy, uses at most 32 tokens, and preserves the image aspect ratio under an 8,847,360-pixel budget.
Training starts from the pinned backbone with seed 20260625 and uses ClickContrast. The repository provides the deterministic SFT-plus-selection-loss command used to reproduce a directly trained checkpoint with comparable performance.