README.md

---
pipeline_tag: text-generation
---

# Parcae-xlarge-1.3B

Parcae is a novel stable, looped architecture for language modeling. Unlike traditional fixed-depth architectures that scale by increasing parameter counts, Parcae increases FLOPs by sending activations through a block of layers in a loop. It addresses instability issues in prior looped models by recasting looping as a nonlinear time-variant dynamical system and constraining the spectral norm of injection parameters.

- **Paper:** [Parcae: Scaling Laws For Stable Looped Language Models](https://huggingface.co/papers/2604.12946)
- **Project Page:** [https://sandyresearch.github.io/parcae/](https://sandyresearch.github.io/parcae/)
- **Repository:** [https://github.com/sandyresearch/parcae](https://github.com/sandyresearch/parcae)

## Installation

To use this model, you can install the `parcae-lm` package:

```bash
pip install parcae-lm
```

## Usage

You can load the pretrained weights using the `parcae_lm` library:

```python
import parcae_lm

# Load this pretrained model from HuggingFace
model = parcae_lm.from_pretrained("SandyResearch/parcae-xlarge-1_3b")
```

## Model Details

This specific checkpoint is the 1.3B parameter variant of Parcae, trained on the FineWeb-Edu dataset.

| Model | Parameters | Prelude | Core | Coda | Model dim. | Recurrence |
|-------|-----------|---------|------|------|-----------|------------|
| Parcae-1.3B | 1.3B | 8 | 8 | 8 | 1536 | 8 |

**Note:** These are base models without any form of downstream modification (instruction tuning, etc.).

## Citation

```bibtex
@misc{prairie2026parcaescalinglawsstable,
      title={Parcae: Scaling Laws For Stable Looped Language Models}, 
      author={Hayden Prairie and Zachary Novack and Taylor Berg-Kirkpatrick and Daniel Y. Fu},
      year={2026},
      eprint={2604.12946},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2604.12946}, 
}
```

## References

This code-base was built on `karpathy/nanochat`, `seal-rg/recurrent-pretraining`, and `Lightning-AI/litgpt`.