metadata

language: en
license: apache-2.0
library_name: transformers

SQFT Base Model: sqft-mistral-7b-v0.3-60-base

Source Model: mistralai/Mistral-7B-v0.3
Sparse Method: Wanda
Sparsity: 60%
Quantization: No

Model Sources

Repository: 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 command in SQFT/run_command/mistral-7b-v0.3/sparse_quantization.sh#11.

Citation

@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={The 2024 Conference on Empirical Methods in Natural Language Processing (Findings)},
  year={2024}
}

Acknowledgement

Thanks to the work Wanda (paper, code), which provides a simple but effective pruning approach.

License

Apache-2.0