|
--- |
|
language: en |
|
license: apache-2.0 |
|
--- |
|
|
|
# SQFT Fine-tuned Model: sqft-sparsepeft-llama-3-8b-30-gsm8k-heu (Patent application requirements, internal use only) |
|
|
|
- Base Model: [IntelLabs/sqft-llama-3-8b-30-base](https://huggingface.co/IntelLabs/sqft-llama-3-8b-30-base) |
|
- Sparsity: 30% |
|
- Quantization: No |
|
- Finetune Method: SQFT + SparsePEFT |
|
- Finetune data: [GSM8K](https://huggingface.co/datasets/openai/gsm8k) |
|
- Sub-Adapter: Heuristic |
|
|
|
### Evaluation |
|
|
|
```bash |
|
lm_eval --model hf --model_args pretrained=${MODEL_PATH},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]() |
|
|
|
## 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} |
|
} |
|
``` |
|
|
|
## License |
|
|
|
Apache-2.0 |
|
|
