GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
wenlongzhao
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
wenlongzhao
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Trained on dongguanting/ARPO-SFT-54K (Tool-Star 54K + STILL), the official ARPO SFT mix.
Trained with LLaMA-Factory full SFT, DeepSpeed ZeRO-3, BF16, and FlashAttention-2.
| Hyperparameter | Value |
|---|---|
| Learning rate | 7e-6 |
| LR schedule | cosine, warmup ratio 0.1 |
| Epochs | 3 |
| Global batch size | 128 |
| Max sequence length |
| 4096 |
| Weight decay | 0.1 |
| Precision | BF16 |
| Seed | 42 |
Final train loss: 0.6852.
Research checkpoint for ARPO-style agentic SFT. Not evaluated as a standalone chat model. Follow the licenses of the base model and the SFT dataset.
bibtex
@article{dong2025arpo,author = {Guanting Dong and Hangyu Mao and Kai Ma and Licheng Bao and Yifei Chen and Zhongyuan Wang and Zhongxia Chen and Jiazhen Du and Huiyang Wang and Fuzheng Zhang and Guorui Zhou and Yutao Zhu and Ji-Rong Wen and Zhicheng Dou},title = {Agentic Reinforced Policy Optimization},journal = {CoRR},volume = {abs/2507.19849},year = {2025},url = {https://arxiv.org/abs/2507.19849}}