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

# SQFT Fine-tuned Model: sqft-qa-sparsepeft-mistral-7b-v0.3-50-gptq-gsm8k-heu

- Base Model: [IntelLabs/sqft-mistral-7b-v0.3-50-base-gptq](https://huggingface.co/IntelLabs/sqft-mistral-7b-v0.3-50-base-gptq)
- Sparsity: 50%
- Quantization: INT4 (GPTQ)
- Finetune Method: SQFT + QA-SparsePEFT
- Finetune data: [GSM8K](https://huggingface.co/datasets/openai/gsm8k)
- Sub-Adapter: Heuristic

### Evaluation

```bash
MODEL_NAME=IntelLabs/sqft-qa-sparsepeft-mistral-7b-v0.3-50-gptq-gsm8k-heu
lm_eval --model hf --model_args pretrained=${MODEL_NAME},add_bos_token=True,trust_remote_code=True --tasks gsm8k --batch_size auto:4
```

Refer to our [repo](https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/SQFT) for the environment information to run this command.

## 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)

## 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",
}
```

## License

Apache-2.0