---
language: en
license: apache-2.0
---

# SQFT Base Model: sqft-llama-3-8b-60-base

- Source Model: [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
- Sparse Method: [Wanda](https://github.com/locuslab/wanda)
- Sparsity: 60%
- Quantization: No

## Model Sources

- **Repository:** [https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/SQFT](https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/SQFT)
- **Paper:** [SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models]()

## How to get this model

Refer to the commands in [SQFT/run_command/llama-3-8b/sparse_quantization.sh#L11](https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/SQFT/run_command/llama-3-8b/sparse_quantization.sh#L11).

## Citation

```bash
@article{munoz2024sqft,
  title = {SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models},
  author={J. Pablo Munoz and Jinjie Yuan and Nilesh Jain},
  journal={},
  year={2024}
}
```

## Acknowledgement

Thanks to the work Wanda ([paper](https://arxiv.org/abs/2306.11695), [code](https://github.com/locuslab/wanda)), which provides a simple but effective pruning approach.

## License

Apache-2.0