GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
XiaofengAlg
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
XiaofengAlg
Model Tree
Qwen/Qwen3-VL-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
MechVL-4B-SFT is initialized from Qwen3-VL-4B-Instruct and trained with full-parameter SFT on the LLM module (vision encoder & projection frozen) over the MechVQA training split. It serves as the reference policy (π_ref) for the subsequent RL stage.
| Base model | Qwen3-VL-4B-Instruct |
| Architecture | Qwen3VLForConditionalGeneration |
| Stage | 1 / 2 — SFT (→ RL) |
| MechVQA Total | 76.36 |
| RL checkpoint | XiaofengAlg/MechVL-4B-RL |
python
import torchfrom transformers import AutoProcessor, AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained( "XiaofengAlg/MechVL-4B-SFT", dtype=torch.bfloat16, device_map="auto")processor = AutoProcessor.from_pretrained("XiaofengAlg/MechVL-4B-SFT") messages = [{"role": "user", "content": [ {"type": "image", "url": "path/to/drawing.png"}, {"type": "text", "text": "图纸中标注的零件总长度是多少？"},]}]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=1024)print(processor.decode(out[0], skip_special_tokens=True))For batch vLLM inference (SFT/RL dual-mode), see scripts/batch_infer.py.
Full-parameter SFT on the LLM module (vision tower frozen) over the MechVQA training split, with a unified response schema (rationale + concise final answer). See §4.1 of the paper.
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 torchfrom transformers import AutoProcessor, AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained( "XiaofengAlg/MechVL-4B-SFT", dtype=torch.bfloat16, device_map="auto")processor = AutoProcessor.from_pretrained("XiaofengAlg/MechVL-4B-SFT") messages = [{"role": "user", "content": [ {"type": "image", "url": "path/to/drawing.png"}, {"type": "text", "text": "图纸中标注的零件总长度是多少？"},]}]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=1024)print(processor.decode(out[0], skip_special_tokens=True))@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}}