GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
zmli
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
zmli
Model Tree
Qwen/Qwen3-VL-2B-Instruct
Input Modalities
Output Modalities
Supported Functionality
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.
| Task | Domain | Input | Output |
|---|---|---|---|
| Scene Graph Generation | Visual | Image | Graph triplets |
| Event Relation Extraction | Text | Document + events | Event relation graph |
| Molecular Graph Description | Scientific | SMILES + graph | Natural language description |
| Graph Algorithmic Reasoning | Algorithmic | Graph description | Algorithm answer |
python
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.
| CT | CD | SP | BM | BLEU-4 | ROUGE-L | PCIs R@50 | MA-S F1 | MA-T F1 | MA-C F1 | HiE F1 |
|---|---|---|---|---|---|---|---|---|---|---|
| 98.41 | 96.97 | 48.59 | 94.54 | 51.53 | 68.47 | 25.38 | 52.20 | 42.68 | 40.91 | 25.15 |
bibtex
@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}}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)@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}}