Model Description

This model is fine-tuned from Qwen3-VL-2B-Instruct using the G-Substrate framework. G-Substrate treats graph structure as a persistent structural substrate that accumulates knowledge across heterogeneous data modalities and tasks. It employs a unified structural schema for compatibility and an interleaved role-based training strategy.

Training Details

• Base model: Qwen3-VL-2B-Instruct
• Training method: Full fine-tuning (SFT) with multi-task learning
• Training data: Scene graphs, event graphs, molecular graphs, graph algorithmic tasks, and interleaved role-based data
• Epochs: 2
• Learning rate: 8e-6 (cosine schedule, warmup 10%)
• Batch size: 1 per device, 32 gradient accumulation steps
• GPUs: 2x NVIDIA A100 (DeepSpeed ZeRO-3)

Supported Tasks

Usage

python
Copy code
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("zmli/G-Substrate-Qwen3-VL-2B", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("zmli/G-Substrate-Qwen3-VL-2B", trust_remote_code=True)

For batch inference with vLLM, see the G-Substrate repository.

Results

Citation

bibtex
Copy code
@inproceedings{li2026gsubstrate,
  title={Graph is a Substrate Across Data Modalities},
  author={Li, Ziming and Wu, Xiaoming and Wang, Zehong and Li, Jiazheng and Tian, Yijun and Bi, Jinhe and Ma, Yunpu and Ye, Yanfang and Zhang, Chuxu},
  booktitle={ICML},
  year={2026}
}