nthngdy/headless-pythia-owt2-70m-raw

Model Sources

• Repository: TBD
• Paper: https://arxiv.org/abs/2309.08351

Model Architecture and Objective

This model is a Pythia-70m architecture trained on OpenWebText-2 using the Contrastive Weight Tying objective.

Software

[More Information Needed]

Citation

BibTeX:

@misc{godey2023headless,
      title={Headless Language Models: Learning without Predicting with Contrastive Weight Tying}, 
      author={Nathan Godey and Éric de la Clergerie and Benoît Sagot},
      year={2023},
      eprint={2309.08351},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Model Card Authors

Nathan Godey Eric de la Clergerie Benoît Sagot

Model Card Contact

[email protected]