Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Tianxiang, Tan, Zhentao, Gong, Tao, Wu, Yue, Chu, Qi, Liu, Bin, Ye, Jieping, Yu, Nenghai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929525547335680
author Chen, Tianxiang
Tan, Zhentao
Gong, Tao
Wu, Yue
Chu, Qi
Liu, Bin
Ye, Jieping
Yu, Nenghai
author_facet Chen, Tianxiang
Tan, Zhentao
Gong, Tao
Wu, Yue
Chu, Qi
Liu, Bin
Ye, Jieping
Yu, Nenghai
contents As a manner to augment pre-trained large language models (LLM), knowledge injection is critical to develop vertical domain large models and has been widely studied. Although most current approaches, including parameter-efficient fine-tuning (PEFT) and block expansion methods, uniformly apply knowledge across all LLM layers, it raises the question: are all layers equally crucial for knowledge injection? We begin by evaluating the importance of each layer in finding the optimal layer range for knowledge injection. Intuitively, the more important layers should play a more critical role in knowledge injection and deserve a denser injection. We observe performance dips in question-answering benchmarks after the removal or expansion of the shallow layers, and the degradation shrinks as the layer gets deeper, indicating that the shallow layers hold the key to knowledge injection. This insight leads us to propose the S strategy, a post-pretraining strategy of selectively enhancing shallow layers while pruning the less effective deep ones. Based on this strategy, we introduce Llama Slayer-8B and Llama Slayer-8B-Instruct. We experimented on the corpus of code $\&$ math and demonstrated the effectiveness of our strategy. Further experiments across different LLM, Mistral-7B, and a legal corpus confirmed the general applicability of the approach, underscoring its wide-ranging efficacy. Our code is available at: \https://github.com/txchen-USTC/Llama-Slayer
format Preprint
id arxiv_https___arxiv_org_abs_2410_02330
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
Chen, Tianxiang
Tan, Zhentao
Gong, Tao
Wu, Yue
Chu, Qi
Liu, Bin
Ye, Jieping
Yu, Nenghai
Computation and Language
As a manner to augment pre-trained large language models (LLM), knowledge injection is critical to develop vertical domain large models and has been widely studied. Although most current approaches, including parameter-efficient fine-tuning (PEFT) and block expansion methods, uniformly apply knowledge across all LLM layers, it raises the question: are all layers equally crucial for knowledge injection? We begin by evaluating the importance of each layer in finding the optimal layer range for knowledge injection. Intuitively, the more important layers should play a more critical role in knowledge injection and deserve a denser injection. We observe performance dips in question-answering benchmarks after the removal or expansion of the shallow layers, and the degradation shrinks as the layer gets deeper, indicating that the shallow layers hold the key to knowledge injection. This insight leads us to propose the S strategy, a post-pretraining strategy of selectively enhancing shallow layers while pruning the less effective deep ones. Based on this strategy, we introduce Llama Slayer-8B and Llama Slayer-8B-Instruct. We experimented on the corpus of code $\&$ math and demonstrated the effectiveness of our strategy. Further experiments across different LLM, Mistral-7B, and a legal corpus confirmed the general applicability of the approach, underscoring its wide-ranging efficacy. Our code is available at: \https://github.com/txchen-USTC/Llama-Slayer
title Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
topic Computation and Language
url https://arxiv.org/abs/2410.02330