GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
CewEhao
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
CewEhao
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
This is the official model card for OPD-Aha-4B, built on
Qwen/Qwen3.5-4B.
OPD-Aha is an on-policy self-distillation framework for improving fine-grained visual perception and multimodal mathematical reasoning. It trains the model with a frozen visual teacher and a counterfactual visual input so that learning focuses on evidence that changes the teacher distribution.
The project provides a vLLM serving entrypoint:
bash
git clone https://github.com/Echochef/OPD-Aha.gitcd OPD-AhaMODEL_PATH=CewEhao/OPD-Aha-4B \SERVED_MODEL_NAME=opd-aha-4b \bash scripts/serve_model.sh
Training, checkpoint merging, inference, and evaluation code is available in
Echochef/OPD-Aha. The repository includes fine-grained
perception evaluation for V*Bench, HR-Bench, MME-RealWorld, and ZoomBench, together with
mathematical reasoning evaluation for MathVista, MathVerse, WeMath, MathVision, and DynaMath.
OPD-Aha builds on Qwen,
verl,
vLLM, and
Vision-OPD.
This model is released under the Apache-2.0 License. The base model and datasets remain subject to their respective licenses.