PyTorch implementation of low-rank adaptation (LoRA), a parameter-efficient approach to adapt a large pre-trained deep learning model which obtains performance on-par with full model fine-tuning.
copied from cf-staging / loralib
https://anaconda.org/conda-forge/loralib/badges/version.svg
https://anaconda.org/conda-forge/loralib/badges/latest_release_date.svg
https://anaconda.org/conda-forge/loralib/badges/latest_release_relative_date.svg
https://anaconda.org/conda-forge/loralib/badges/platforms.svg
https://anaconda.org/conda-forge/loralib/badges/license.svg
https://anaconda.org/conda-forge/loralib/badges/downloads.svg