---
pipeline_tag: text-generation
language:
- en
datasets:
- allenai/c4
---

This is a 800M parameters model pre-trained with [QuEST](https://huggingface.co/papers/2502.05003) over 80B C4 tokens in INT4 format (W4A4).

The code to verify that this model works in INT4 can be found [here](https://github.com/IST-DASLab/QuEST/blob/main/src/HadamardTesting.ipynb).