You can deploy this model and start earning money today!

DepthMuun/
gfn-isn-shakespeare-char

Name: gfn-isn-shakespeare-char
Availability: InStock

gfn

physics-informed

geometric-deep-learning

Views

No views yet

ISN Shakespeare: Character-level Language Model

DOI: 10.5281/zenodo.19141132

Models: Hugging Face

GitHub: GFN Framework

This repository contains the weights and configuration for a Shakespeare-style language model built using the Inertial State Network (ISN) architecture.

🚀 Highlights

Architecture: Inertial State Network (ISN).
Parameters: 363,329 (Equivalent to nanoGPT baseline).
Inference Efficiency: Constant O(1) VRAM and O(1) per-step time scaling.
Performance: 2.48 PPL on TinyShakespeare (Official).

💻 Technical Usage (Inference)

To run inference locally, you need the GFN Framework installed.

1. Install GFN Framework

pip install gfn==v2.7.0

2. Clone this repository

bash

git lfs install
git clone https://huggingface.co/DepthMuun/gfn-isn-shakespeare-char
cd gfn-isn-shakespeare-char

3. Run Inference Script

The repository includes an inference.py script for interactive generation:

python inference.py

Python API Example (Manual Assembly)

As shown in the audited inference.py, the official way to load ISN models is:

python

import torch
import json
from gfn import isn

# 1. Load Config
with open("config.json", "r") as f:
    config = json.load(f)

# 2. Instantiate Model (Manual Schema)
model = isn.create(
    vocab_size=65,  # Unique characters in tinyshakespeare.txt
    d_model=config['model']['d_model'],
    d_embedding=config['model']['d_embedding'],
    d_properties=config['model']['d_properties'],
    scanner_cls=isn.GFNScanner,
    world_cls=isn.GFNWorld,
    emitter_cls=isn.GFNEmitter
).to("cpu")

# 3. Load State Dict
checkpoint = torch.load("best_model.pt", map_location="cpu")
model.load_state_dict(checkpoint['model_state_dict'])
model.eval()

# 4. Generate Text
# Use model.generate() or the provided inference.py CLI

📜 Citation

If you use this work, please cite:

bibtex

@article{sturtz2026gfn,
  title     = {Geometric Flow Networks: A Physics-Informed Paradigm for Sequential Intelligence},
  author    = {St{\"u}rtz, Joaqu{\'i}n},
  journal   = {GFN Research Preprint},
  year      = {2026},
  publisher = {DepthMuun Research},
  doi       = {10.5281/zenodo.19141132},
  url       = {https://doi.org/10.5281/zenodo.19141132}
}

🔗 Resources

Interactive Demo: Hugging Face Space
Framework Source: GitHub: DepthMuun/gfn
Official Paper: Zenodo