MUMBAI, India, Sept. 26 -- Intellectual Property India has published a patent application (202441022184 A) filed by L&T Technology Services Limited, Chennai, Tamil Nadu, on March 22, 2024, for 'method and system for compressing and tuning large language models.'
Inventor(s) include Sudhir Bhadauria; and Vikram Subramani.
The application for the patent was published on Sept. 26, under issue no. 39/2025.
According to the abstract released by the Intellectual Property India: "A method (300) and a system (100) of compressing and tuning large language models is disclosed. A processor 104 receives an LLM, a pruning ratio, an initial rank, and a set of target layers from a plurality of layers of the LLM. A dependency-wise pruning is performed of the LLM based on the pruning ratio. A rank-based factorization of the LLM is performed based on the initial rank to generate factorized weights. A pruned LLM is determined based on the dependency-wise pruning. The pruned LLM is updated by injecting one or more additional layers to one or more corresponding layers of the pruned LLM to generate a compressed LLM. The compressed LLM is fine-tuned for a specific domain or for a specific task by fine-tuning the factorized weights for the additional layers of the compressed LLM based on the domain-specific training data or task-specific training data."
Disclaimer: Curated by HT Syndication.
