sqft-mistral-7b-v0.3-50-base/README.md

---
language: en
license: apache-2.0
library_name: transformers
---

# SQFT Base Model: sqft-mistral-7b-v0.3-50-base

- Source Model: [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3)
- Sparse Method: [Wanda](https://github.com/locuslab/wanda)
- Sparsity: 50%
- 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](https://arxiv.org/abs/2410.03750)
- [Low-Rank Adapters Meet Neural Architecture Search for LLM Compression](https://arxiv.org/abs/2501.16372)

## How to get this model

Refer to the command in [SQFT/run_command/mistral-7b-v0.3/sparse_quantization.sh#11](https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/SQFT/legacy/run_command/mistral-7b-v0.3/sparse_quantization.sh#11).

## Citation

```bash
@inproceedings{munoz-etal-2024-sqft,
    title = "{SQFT}: Low-cost Model Adaptation in Low-precision Sparse Foundation Models",
    author = "Munoz, Juan Pablo  and
      Yuan, Jinjie  and
      Jain, Nilesh",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.749",
    pages = "12817--12832",
}
```

## 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