本仓库包含专为 XOR 逻辑设计的测地状态空间模型(G-SSM) 的权重与配置。
要在本地运行推理,需安装GFN 框架。
pip install gfngit lfs install
git clone https://huggingface.co/DepthMuun/gfn-gssm-xor-parity
cd gfn-gssm-xor-parity使用附带的 inference.py 脚本进行交互式测试:
python inference.py如经过审核的 inference.py 所示,加载 G-SSM 模型的官方方法如下:
import torch
from gfn import gssm
# Load model (automatically handles config.json in the same dir)
model = gssm.load("xor_best_model.bin", device="cpu")
model.eval()
# Inference
bits = torch.randint(0, 2, (1, 1000000))
with torch.no_grad():
logits, state, info = model(bits)
# Geometrical decoding logic is detailed in inference.py如果您使用了本研究成果,请引用:
@article{sturtz2026geometry,
title={Geometric Flow Networks: A Physics-Informed Paradigm for Sequential Intelligence},
author={Stürtz, Joaquín},
journal={Zenodo Preprints},
year={2026},
doi={10.5281/zenodo.19141133},
url={https://doi.org/10.5281/zenodo.19141133}
}