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-30B-A3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Benchmark | Accuracy | Semantic error |
|---|---|---|
| ScreenSpot-Pro | 65.53 | 27.45 |
| UI-Vision | 37.92 | 45.92 |
| OSWorld-G | 72.55 | 17.45 |
UI-Vision is the equal-weight macro over its basic, functional, and spatial element-grounding subsets. OSWorld-G uses its 510 target-bearing examples; refusal-only rows are excluded. These public benchmarks were used during model selection, so results are test-tuned rather than held-out validation estimates.
bash
python evaluate.py \--model ruotian/SelectGround-30B-A3B \--benchmark screenspot_pro \--data data/screenspot-pro \--output outputs/screenspot-pro.jsonl
The loader restores visual_merger.pt in addition to the PEFT adapter.
Inference uses the full screenshot, Qwen smart resize with
min_pixels=3136,max_pixels=8847360, greedy decoding for at most 32 tokens,
and normalized 0–1000 point coordinates.
bash
hf download ruotian/ContrastGround --repo-type dataset \--local-dir data/ContrastGroundPYTORCH_CUDA_ALLOC_CONF=expandable_segments:True \accelerate launch --mixed_precision bf16 --num_processes 4 train.py \--model 30b \--data data/ContrastGround \--pairs-file data/ContrastGround/data/selectground-30b-a3b/train_pairs.jsonl \--replay-file data/ContrastGround/data/selectground-30b-a3b/train_replays.jsonl \--output outputs/SelectGround-30B-A3B \--steps 200 --gpus 4 --accumulation 4 \--learning-rate 3.5e-5 --selector-learning-rate 1e-4 \--aux-weight 0.125 --ground-coordinate-weight 1.0 \--margin 0.3 --pair-weight 0.5 \--warmup-steps 10 --scheduler-steps 200 \--holdout-fraction 0.02 --seed 20260819
This is SFT coordinate cross-entropy on pair and replay rows plus the paper's
auxiliary competitor-selection loss on pair rows. Pair and replay microbatches
alternate. LoRA uses rank 64, alpha 128, dropout 0.05 on
q/k/v/o/gate/up/down projections. The selector reads semantic attention from
layers 18–23. See training_manifest.json for the complete recipe and artifact
SHA-256 checksums.
The reference environment used PyTorch 2.11.0+cu128, Transformers 4.57.1, PEFT 0.19.1, Accelerate 1.13.0, and qwen-vl-utils 0.0.14. CUDA kernels are not bitwise deterministic; clean runs should be expected to be close rather than byte-identical.
The adapter follows the Apache-2.0 license of the base model. Dataset assets retain their upstream terms; consult the ContrastGround data card and its row-level provenance.