Tulu-Geo-DiT-v1 🌍

Tulu-Geo-DiT-v1 is a specialized Diffusion Transformer (DiT) architecture optimized for factual geography retrieval.

πŸ›  Usage

The model weights (tulu_geo_expert.pt) are designed to be used with the pipeline.py script.

from pipeline import generate_expert

# 150 Denoising Steps -> Factual Output
print(generate_expert("The capital of France is"))

πŸ“„ Citation

If you use this model or code in your research, please cite it as follows:

@software{lordxmen2k_tulu_geo_2025,
  author = {Gerald Enrique Nelson Mc Kenzie},
  title = {Tulu-Geo-Diffusion: Factual Retrieval via Latent Denoising in Diffusion Transformers},
  year = {2025},
  publisher = {Zenodo},
  version = {v1.0.0},
  doi = {10.5281/zenodo.18030750},
  url = {https://doi.org/10.5281/zenodo.18030750}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for LordXmen2k/Tulu-Geo-DiT-v1

Finetuned
(6255)
this model