Modernbert Large Zeroshot V1

🚀 ModernBERT-large-zeroshot-v1

This is a fine - tuned ModernBERT - large model for zero - shot classification, trained on specific datasets to handle natural language inference tasks.

🚀 Quick Start

To use this model, you first need to install the necessary libraries. You can use the following command:

pip install transformers torch datasets

Here is a simple example of using the model for zero - shot classification:

classifier = pipeline("zero-shot-classification", "r-f/ModernBERT-large-zeroshot-v1")
sequence_to_classify = "I want to be an actor."
candidate_labels = ["space", "economy", "entertainment"]
output = classifier(sequence_to_classify, candidate_labels, multi_label=False)
print(output)
>>{'sequence': 'I want to be an actor.', 'labels': ['entertainment', 'space', 'economy'], 'scores': [0.9614731073379517, 0.028852475807070732, 0.009674412198364735]}

✨ Features

• This model is a fine - tuned ModernBERT - large for Natural Language Inference.
• It is designed to carry out zero - shot classification.

📦 Installation

pip install transformers torch datasets

💻 Usage Examples

Basic Usage

classifier = pipeline("zero-shot-classification", "r-f/ModernBERT-large-zeroshot-v1")
sequence_to_classify = "I want to be an actor."
candidate_labels = ["space", "economy", "entertainment"]
output = classifier(sequence_to_classify, candidate_labels, multi_label=False)
print(output)
>>{'sequence': 'I want to be an actor.', 'labels': ['entertainment', 'space', 'economy'], 'scores': [0.9614731073379517, 0.028852475807070732, 0.009674412198364735]}

📚 Documentation

Model Overview

Model Card

Performance Metrics

• Training Loss: Measures the model's fit to the training data.
• Validation Loss: Measures the model's generalization to unseen data.
• Accuracy: The percentage of correct predictions over all examples.
• F1 Score: A balanced metric between precision and recall.

Training Details

• Model: ModernBERT (Large variant)
• Framework: PyTorch
• Batch Size: 32
• Learning Rate: 2e-5
• Optimizer: AdamW
• Hardware: RTX 4090

🔧 Technical Details

The model is a fine - tuned version of ModernBERT - large for Natural Language Inference. It was trained on the MoritzLaurer/synthetic_zeroshot_mixtral_v0.1 dataset. The fine - tuning process is aimed at enabling the model to perform zero - shot classification tasks.

📄 License

This model is licensed under the MIT License. See the LICENSE file for more details.

Acknowledgments

• The model was trained on the MoritzLaurer/synthetic_zeroshot_mixtral_v0.1. And the training script was adapted from MoritzLaurer/zeroshot-classifier
• Special thanks to the Hugging Face community and all contributors to the transformers library.