mjwagerman/bias-detector

Bias Detector

This model is fine-tuned using PEFT LoRA on existing Hugging Face models to classify and evaluate the bias in news sources.

Model Details

• Architecture: Transformer-based (e.g., BERT, RoBERTa)
• Fine-tuning Method: Parameter Efficient Fine-Tuning (LoRA)
• Use Case: Bias classification, text summarization, sentiment analysis
• Dataset: ...
• Training Framework: PyTorch + Transformers

Usage

To use this model, install the necessary libraries:

pip install transformers torch

Then load the model with:

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model_name = "mjwagerman/bias-detector"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

text = "This is an example news headline."
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)