GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
MonteXiaofeng
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
MonteXiaofeng
Model Tree
Qwen/Qwen3-VL-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
MechVL-4B-RL is obtained by further optimizing MechVL-4B-SFT with DAPO (Decoupled Clip and Dynamic Sampling Policy Optimization) in a two-stage self-play regime:
Reward = Accuracy (LLM-as-a-Judge, semantic equivalence in [0,1]) + Format (binary, well-formed <think>/<answer>) + Quality (Logic / Professionalism / Conciseness).
| Base model | Qwen3-VL-4B-Instruct |
| Architecture | Qwen3VLForConditionalGeneration |
| Stage | 2 / 2 — RL (DAPO self-play, on top of SFT) |
| MechVQA Total | 84.85 (best across open- & closed-source MLLMs) |
| SFT checkpoint | MonteXiaofeng/MechVL-4B-SFT |
The model reasons then answers, enclosed as:
text
<think> ...reasoning... </think><answer> ...final answer... </answer>Parse the <answer>...</answer> span for the final answer (a regex like <answer>(.*?)</answer> works).
python
import re, torchfrom transformers import AutoProcessor, AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained( "MonteXiaofeng/MechVL-4B-RL", dtype=torch.bfloat16, device_map="auto")processor = AutoProcessor.from_pretrained("MonteXiaofeng/MechVL-4B-RL") question = "图纸中标注的零件总长度是多少？"# RL format prompt (matches training): question + <think>/<answer> instructionmessages = [{"role": "user", "content": [ {"type": "image", "url": "path/to/drawing.png"}, {"type": "text", "text": question},]}]inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to(model.device)out = model.generate(**inputs, max_new_tokens=4096, do_sample=True, temperature=0.6, top_p=0.95, top_k=20)text = processor.decode(out[0], skip_special_tokens=True)m = re.search(r"<answer>(.*?)</answer>", text, re.DOTALL)print("answer:", m.group(1).strip() if m else text)For batch vLLM inference with the exact training-time format prompt, see scripts/batch_infer.py (MODE=rl) and prompts/mech_r1.jinja.
On the MechVQA benchmark (Total score):
| Model | Total |
|---|---|
| GPT-5 | 75.44 |
| Gemini-3-Pro-Preview | 77.28 |
| GLM-4.6V (best closed-source) | 78.91 |
| MechVL-4B-SFT | 76.36 |
| MechVL-4B-RL (this model) | 84.85 |
See §6 of the paper for the full table and ablations (DAPO > GRPO > GSPO; two-stage self-play; reward-component ablations).
bibtex
@misc{kou2026mechvqabenchmarkingenhancingmultimodal, title={MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding}, author={Qian Kou and Xiaofeng Shi and Yulin Li and Xiaosong Qiu and Xinyang Wang and Hua Zhou and Cao Dongxing}, year={2026}, eprint={2605.30794}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2605.30794}}Apache-2.0.
import re, torchfrom transformers import AutoProcessor, AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained( "MonteXiaofeng/MechVL-4B-RL", dtype=torch.bfloat16, device_map="auto")processor = AutoProcessor.from_pretrained("MonteXiaofeng/MechVL-4B-RL") question = "图纸中标注的零件总长度是多少？"# RL format prompt (matches training): question + <think>/<answer> instructionmessages = [{"role": "user", "content": [ {"type": "image", "url": "path/to/drawing.png"}, {"type": "text", "text": question},]}]inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to(model.device)out = model.generate(**inputs, max_new_tokens=4096, do_sample=True, temperature=0.6, top_p=0.95, top_k=20)text = processor.decode(out[0], skip_special_tokens=True)m = re.search(r"<answer>(.*?)</answer>", text, re.DOTALL)print("answer:", m.group(1).strip() if m else text)@misc{kou2026mechvqabenchmarkingenhancingmultimodal, title={MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding}, author={Qian Kou and Xiaofeng Shi and Yulin Li and Xiaosong Qiu and Xinyang Wang and Hua Zhou and Cao Dongxing}, year={2026}, eprint={2605.30794}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2605.30794}}