MindMiner Documentation

Introduction

MindMiner is a text classification model developed to uncover linguistic markers of mind perception, providing insights into consumer-smart object relationships. This tool leverages the capabilities of the Transformers library and PyTorch framework, specifically utilizing the RoBERTa architecture.

Architecture

MindMiner is built on the RoBERTa model, a robust variant of the BERT architecture, optimized for NLP tasks like text classification. It is designed to function seamlessly with the Transformers library and PyTorch, enabling efficient model training and inference.

Training

The model is trained to detect specific linguistic patterns that indicate how consumers perceive smart objects. The training process involves fine-tuning RoBERTa on a dataset annotated with these linguistic markers, optimizing the model's ability to classify text according to the defined parameters.

Guide: Running Locally

To run MindMiner locally, follow these steps:

1. Install the Transformers Library: Ensure you have the Transformers library installed. You can do this with pip:

   pip install transformers
   

2. Set Up the Model: Use the following Python code to initialize the MindMiner pipeline:

   from transformers import pipeline
   model_name = "j-hartmann/MindMiner"
   mindminer = pipeline(model=model_name, function_to_apply="none", device=0)
   

3. Run Inference: Input text can be processed through the initialized pipeline to obtain classification results.

4. Hardware Recommendations: For optimal performance, especially during large-scale inference, consider using cloud-based GPUs. Platforms such as AWS, Google Cloud, or Azure offer suitable GPU instances.

License

The MindMiner model documentation and source code are subject to the licensing terms provided in the original repository. Users should review the specific license to ensure compliance with its terms and conditions.