Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 2129-2145
Abstract
Parsa Kavehzadeh, Mojtaba Valipour, Marzieh Tahaei, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh. Findings of the Association for Computational Linguistics: EACL 2024. 2024.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- KronA: Parameter-Efficient Tuning with Kronecker Adapter2025
- A Survey on Model Compression for Large Language ModelsTransactions of the Association for Computational Linguistics, 2024
- The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only2023
- DyLoRA: Parameter-Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation2023
- Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes2023
- Self-Instruct: Aligning Language Models with Self-Generated Instructions2023
- Training Language Models to Follow Instructions with Human Feedback2022
- Training Compute-Optimal Large Language Models2022
- AdapterFusion: Non-Destructive Task Composition for Transfer Learning2021
- DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference2020