Liu O. Martin
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes an aggressive, parameter-efficient method to prune non-essential experts from Mixture-of-Experts (MoE) LLMs, significantly compressing the model while maintaining high machine translation quality.
The paper proposes an aggressive, parameter-efficient method to prune non-essential experts from Mixture-of-Experts (MoE) LLMs, significantly compressing the model while maintaining high machine translation quality.
Papers
Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts
The paper proposes an aggressive, parameter-efficient method to prune non-essential experts from Mixture-of-Experts (MoE) LLMs, significantly compressing the model while maintaining high machine trans…