---
license: mit
datasets:
- the_pile_openwebtext2
language:
- en
pipeline_tag: text-generation
---

### Model Sources

<!-- Provide the basic links for the model. -->

- **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:**

```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

nathan.godey@inria.fr