Efficient Large Language Model
Collection
Shortened LLMs from Depth Pruning; https://github.com/Nota-NetsPresso/shortened-llm
•
14 items
•
Updated
•
4
Shortened LLaMA is a depth-pruned version of LLaMA models & variants for efficient text generation.
After identifying unimportant Transformer blocks, we perform one-shot pruning and light LoRA-based retraining.
Source Model |
Pruning Ratio |
Pruning Criterion |
HF Models Link |
---|---|---|---|
LLaMA-1-7B | 20% | PPL | nota-ai/st-llama-1-5.5b-ppl |
LLaMA-1-7B | 20% | Taylor+ | nota-ai/st-llama-1-5.5b-taylor |
Vicuna-v1.3-7B | 20% | PPL | nota-ai/st-vicuna-v1.3-5.5b-ppl |
Vicuna-v1.3-7B | 20% | Taylor+ | nota-ai/st-vicuna-v1.3-5.5b-taylor |
Vicuna-v1.3-13B | 21% | PPL | nota-ai/st-vicuna-v1.3-10.5b-ppl |
Vicuna-v1.3-13B | 21% | Taylor+ | nota-ai/st-vicuna-v1.3-10.5b-taylor |
@article{kim2024shortened,
title={Shortened LLaMA: A Simple Depth Pruning for Large Language Models},
author={Kim, Bo-Kyeong and Kim, Geonmin and Kim, Tae-Ho and Castells, Thibault and Choi, Shinkook and Shin, Junho and Song, Hyoung-Kyu},
journal={arXiv preprint arXiv:2402.02834},
year={2024},
url={https://arxiv.org/abs/2402.02834}
}
@article{kim2024mefomo,
title={Shortened LLaMA: A Simple Depth Pruning for Large Language Models},
author={Kim, Bo-Kyeong and Kim, Geonmin and Kim, Tae-Ho and Castells, Thibault and Choi, Shinkook and Shin, Junho and Song, Hyoung-Kyu},
journal={ICLR Workshop on Mathematical and Empirical Understanding of Foundation Models (ME-FoMo)},
year={2024},
url={https://openreview.net/forum?id=18VGxuOdpu}
}