GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
jiangchengsong
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
jiangchengsong
Model Tree
Qwen/Qwen2.5-1.5B
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "jiangchengsong/MemDuet-S1-Qwen2.5-1.5B"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype="auto")model.eval()Use Transformers 5.15.0 with PyTorch 2.13.0, matching the prepared release. For the selection prompt and the complete controller, use the MemDuet inference implementation.
From the MemDuet code directory, download this model to system1:
bash
hf download jiangchengsong/MemDuet-S1-Qwen2.5-1.5B --local-dir system1python -m memduet serve --config configs/paper_frozen.json --role selectorFollow the code repository instructions to provide system2, start its service,
and run evaluation. Retain this model's tokenizer and chat template.
Apache License 2.0. The base-model license is included in LICENSE; source
attribution and modification information are retained in NOTICE.
bibtex
@misc{song2026memduet, title = {MemDuet: Learning Dual-Process Memory for Long-Context Reasoning}, author = {Song, Jiangcheng and Jing, Haodong and Mu, Yulin and Tao, Lesong and Wang, Jixin and Cui, Jin and Ren, Tianjing and Xie, Runxuan and Ma, Yongqiang and Zheng, Nanning}, year = {2026}, eprint = {2610.19928}, archivePrefix = {arXiv}, primaryClass = {cs.CL}, url = {https://arxiv.org/abs/2610.19928}}@misc{song2026memduet, title = {MemDuet: Learning Dual-Process Memory for Long-Context Reasoning}, author = {Song, Jiangcheng and Jing, Haodong and Mu, Yulin and Tao, Lesong and Wang, Jixin and Cui, Jin and Ren, Tianjing and Xie, Runxuan and Ma, Yongqiang and Zheng, Nanning}, year = {2026}, eprint = {2610.19928}, archivePrefix = {arXiv}, primaryClass = {cs.CL}, url = {https://arxiv.org/abs/2610.19928}}