MUMBAI, India, June 19 -- Intellectual Property India has published a patent application (202441095071 A) filed by L&t Technology Services Limited on December 03, 2024, for Method And System For Fine-Tuning Large Language Models.
Inventors include Sudhir Bhadauria; and Vikram Subramani.
The application for the patent was published on June 05, 2026, under issue no. 23/2026.
Abstract: A method (300) and a system (100) of fine-tuning large language models is disclosed. The method includes receiving a user input (212) corresponding to an LLM (214). The user input includes a selection of a set of target layers (216), predefined scoring criteria (218), and a distribution ratio (220). The method further includes determining a score corresponding to each of a plurality of weights of each of the set of target layers based on the predefined scoring criteria; for each of the set of target layers, classifying the plurality of weights into a set of trainable weights and a set of non-trainable weights based on the score and the distribution ratio (220); and for each of the set of target layers, modifying the set of trainable weights using a domain-specific training dataset to obtain a fine-tunned LLM (224). FIG. 2
Disclaimer: Curated by HT Syndication.
