May 21, 2024
Towards Modular LLMs by Building and Reusing a Library of LoRAs
Posted by Cecile G. Tamura in category: futurism
From Microsoft.
Towards Modular LLMs by Building and Reusing a Library of LoRAs https://huggingface.co/papers/2405.
The growing number of parameter-efficient adaptations of a base large language model (LLM) calls for studying whether we can reuse such trained adapters to improve performance for…
Continue reading “Towards Modular LLMs by Building and Reusing a Library of LoRAs” »