library_name: transformers
tags:
- sentiment-analysis
- multilingual
- lora
- xlm-roberta
- peft
Trilingual Sentiment LoRA Model
Model Summary
Trilingual Sentiment LoRA is a fine-tuned XLM-RoBERTa model optimized for multilingual sentiment classification across Arabic, English, and Spanish texts.
It applies Low-Rank Adaptation (LoRA) using the PEFT framework, enabling efficient fine-tuning while maintaining robust multilingual understanding.
Model Details
- Developed by: Osama Naguib
- Funded by: Ahmed Zaky
- Model Type: Sequence Classification
- Languages: Arabic, English, Spanish
- License: MIT
- Finetuned From: xlm-roberta-base
- Frameworks: Transformers, Datasets, PEFT, PyTorch
Model Sources
- Repository: https://huggingface.co/osamanaguib/trilingual-sentiment-lora
- Base Model: https://huggingface.co/xlm-roberta-base
Intended Uses
Direct Use
This model can be used directly for sentiment classification on multilingual (EN/ES/AR) text data.
Example labels:
- 0 → Negative
- 1 → Neutral
- 2 → Positive
Example use: library_name: transformers tags: [sentiment-analysis, multilingual, lora, xlm-roberta, peft]
Trilingual Sentiment LoRA Model
Model Summary
Trilingual Sentiment LoRA is a fine-tuned XLM-RoBERTa model optimized for multilingual sentiment classification across Arabic, English, and Spanish texts.
It applies Low-Rank Adaptation (LoRA) using the PEFT framework, enabling efficient fine-tuning while maintaining robust multilingual understanding.
Model Details
- Developed by: Osama Naguib
- Funded by: Ahmed Zaky
- Model Type: Sequence Classification
- Languages: Arabic, English, Spanish
- License: MIT
- Finetuned From: xlm-roberta-base
- Frameworks: Transformers, Datasets, PEFT, PyTorch
Model Sources
- Repository: https://huggingface.co/osamanaguib/trilingual-sentiment-lora
- Base Model: https://huggingface.co/xlm-roberta-base
Intended Uses
Direct Use
This model can be used directly for sentiment classification on multilingual (EN/ES/AR) text data.
Example labels:
- 0 → Negative
- 1 → Neutral
- 2 → Positive
Example use: