NOTICE
Copyright (c) 2025 Authors of Data-Efficient Adaptation and a Novel Evaluation Method for Aspect-based Sentiment Analysis.
The "EduRABSA_SLM" LoRA adaptors and any merged models derived from them, including this model, are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0).
Attribution is required. You may not use this model for commercial purposes. Any derivatives must be shared under CC BY-NC-SA 4.0.
This merged model combines components under multiple licenses:
LoRA Adapter
Copyright (c) 2025 Authors of Data-Efficient Adaptation and a Novel Evaluation Method for Aspect-based Sentiment Analysis.
Licensed under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/
Base Model
The base model of this work is Phi4-mini-instruct licensed under the MIT License.
Copyright (c) Microsoft Corporation.
See
LICENSE_BASE_MODEL_MIT.txtin each model sub-directory for the full license text.
Other third-party software and data used
The LoRA adapters were trained using tools from the Hugging Face
Transformerslibrary under the Apache 2.0 licence.The base model used flash-attention which copyright notice is included in
NOTICE_FLASH_ATTENTION.mdin each model sub-directory.The weight-merging used ArceeAI's
mergekitlibrary under the GNU Lesser General Public License v3.0, which file is included inLICENSE_MERGEKIT_GNU.txtin each model sub-directory.The onnx conversion and quantisation used Microsoft
onnxruntime-genailibrary under the MIT licence.This LoRA adapters were trained using the EduRABSA dataset licensed under CC BY-NC-SA 4.0.