Despite the remarkable success of Large Language Models (LLMs), the massive
size poses significant deployment challenges, particularly on
resource-constrained hardware. While existing LLM compression methods focus on
quantization, pruning remains relatively unexplored due to the high cost of
training-based approaches and data collection challenges. One-shot pruning
methods, although cost-effective and data-free, have become dominant in LLM
pruning, but lead to performance decline under the structured pruning setting.
In this work, we introduce a new paradigm for structurally pruning LLMs, called
Compresso. Our approach, through the collaboration of the proposed
resource-efficient pruning algorithm and the LLM itself, learns optimal pruning
decisions during the training process. Compresso addresses the challenges of
expensive training costs and data collection by incorporating Low-Rank
Adaptation (LoRA) into the $L_0$ regularization during the instruction tuning
process. Then, we further augment the pruning algorithm by introducing a
collaborative prompt that fosters collaboration between the LLM and the pruning
algorithm, significantly boosting the overall performance. To this end,
Compresso prunes LLaMA-7B to 5.4B, maintaining original performance and even
surpassing LLaMA-7B in reading comprehension by 2.62%. Extensive experiments
demonstrate that Compresso significantly outperforms one-shot pruning baselines
across various sparsity ratios, achieving up to 2.21%, 11.43%, 7.04%, and 4.81%
higher scores on the commonsense reasoning, reading comprehension, MMLU, and
BBH benchmarks, respectively.

通过合作的剪枝算法和大型语言模型自身，在数据收集和训练成本昂贵的挑战下，Compresso 通过在训练过程中学习最优的剪枝决策以及引入协同提示进一步增强了剪枝算法，成功将 LLaMA-7B 剪枝至 5.4B，并在阅读理解上超过 LLaMA-7B2.62%，在共同推理、阅读理解、MMLU 和 BBH 基准测试上分别获得了 2.21%、11.43%、7.04% 和 4.81% 的更高分数，明显优于一次性剪枝基线。