RichardErkhov/IntelLabs_-_sqft-sparsepeft-phi-3-mini-4k-50-math-heu-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

sqft-sparsepeft-phi-3-mini-4k-50-math-heu - GGUF

• —Model creator: https://huggingface.co/IntelLabs/
• —Original model: https://huggingface.co/IntelLabs/sqft-sparsepeft-phi-3-mini-4k-50-math-heu/

Original model description: --- language: en license: apache-2.0 library_name: transformers ---

SQFT Fine-tuned Model: sqft-sparsepeft-phi-3-mini-4k-50-math-heu

• —Base Model: IntelLabs/sqft-phi-3-mini-4k-50-base
• —Sparsity: 50%
• —Quantization: No
• —Finetune Method: SQFT + SparsePEFT
• —Finetune data: 10K instruction-following math reasoning training dataset from LLM-Adapters (math_10k.json)
• —Sub-Adapter: Heuristic

Evaluation

git clone https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning.git haaml && cd haaml/SQFT

MODEL_NAME=IntelLabs/sqft-sparsepeft-phi-3-mini-4k-50-math-heu
OUTPUT_DIR=./results
python eval/evaluate_math.py --base_model_path ${MODEL_NAME} --output_dir ${OUTPUT_DIR}

Refer to our repo for the environment information to run this command.

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]()

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={},
  year={2024}
}

License

Apache-2.0