GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ybrrraway
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
ybrrraway
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
🎯 Key Benefits:
QVS-Bench is a diagnostic benchmark for systematically evaluating how the quantity of image inputs impacts spatial reasoning accuracy. It maintains a substantially uniform proportional distribution across five input scale configurations (1, 4, 8, 12, and 16 frames), ensuring fair and unbiased analysis of the relevant mechanisms.
bash
conda create -n v2lo python=3.10 -yconda activate v2lopip install -r requirements.txtbash
# SFT trainingbash src/ms-swift/sft.sh# Merge modelbash src/ms-swift/merge_lora.sh # RL trainingbash src/EasyR1/examples/rl.sh# Merge modelcd src/EasyR1python3 scripts/model_merger.py --local_dir checkpoints/easy_r1/exp_name/global_step_1/actorbibtex
@misc{2511.16160,Author = {Yibin Huang and Wang Xu and Wanyue Zhang and Helu Zhi and Jingjing Huang and Yangbin Xu and Yangang Sun and Conghui Zhu and Tiejun Zhao},Title = {Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning},Year = {2025},Eprint = {arXiv:2511.16160},}@misc{2511.16160,Author = {Yibin Huang and Wang Xu and Wanyue Zhang and Helu Zhi and Jingjing Huang and Yangbin Xu and Yangang Sun and Conghui Zhu and Tiejun Zhao},Title = {Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning},Year = {2025},Eprint = {arXiv:2511.16160},}