Roberta Large Zeroshot V2.0 C

🚀 roberta-large-zeroshot-v2.0-c

This model is designed for efficient zeroshot classification, capable of performing classification tasks without training data and running on both GPUs and CPUs.

🚀 Quick Start

The roberta-large-zeroshot-v2.0-c model is part of the zeroshot-v2.0 series, which is designed for efficient zeroshot classification using the Hugging Face pipeline. These models can perform classification tasks without the need for training data and can run on both GPUs and CPUs.

✨ Features

• Efficient Zeroshot Classification: These models can perform classification tasks without the need for training data.
• Universal Classification Task: They can determine whether a hypothesis is "true" or "not true" given a text, based on the Natural Language Inference task (NLI).
• Commercially-Friendly Data: Some models in the series are trained on fully commercially-friendly data, suitable for users with strict license requirements.

📦 Installation

To use this model, you need to install the transformers library. You can install it using the following command:

!pip install transformers[sentencepiece]

💻 Usage Examples

Basic Usage

from transformers import pipeline
text = "Angela Merkel is a politician in Germany and leader of the CDU"
hypothesis_template = "This text is about {}"
classes_verbalized = ["politics", "economy", "entertainment", "environment"]
zeroshot_classifier = pipeline("zero-shot-classification", model="MoritzLaurer/deberta-v3-large-zeroshot-v2.0")  # change the model identifier here
output = zeroshot_classifier(text, classes_verbalized, hypothesis_template=hypothesis_template, multi_label=False)
print(output)

Advanced Usage

multi_label=False forces the model to decide on only one class. multi_label=True enables the model to choose multiple classes.

📚 Documentation

Model description

The zeroshot-v2.0 series of models are designed for efficient zeroshot classification with the Hugging Face pipeline. These models can perform classification without training data and run on both GPUs and CPUs. An overview of the latest zeroshot classifiers is available in the Zeroshot Classifier Collection.

The main update of this zeroshot-v2.0 series of models is that several models are trained on fully commercially-friendly data for users with strict license requirements.

These models can perform one universal classification task: determine whether a hypothesis is "true" or "not true" given a text (entailment vs. not_entailment). This task format is based on the Natural Language Inference task (NLI). The task is so universal that any classification task can be reformulated into this task by the Hugging Face pipeline.

Training data

Models with a "-c" in the name are trained on two types of fully commercially-friendly data:

1. Synthetic data: Generated with Mixtral-8x7B-Instruct-v0.1. The final dataset used is available in the synthetic_zeroshot_mixtral_v0.1 dataset in the subset mixtral_written_text_for_tasks_v4.
2. Commercially-friendly NLI datasets: (MNLI, FEVER-NLI). These datasets were added to increase generalization.

Models without a "-c" in the name also included a broader mix of training data with a broader mix of licenses: ANLI, WANLI, LingNLI, and all datasets in this list where used_in_v1.1==True.

Metrics

The models were evaluated on 28 different text classification tasks with the f1_macro metric. The main reference point is facebook/bart-large-mnli which is, at the time of writing (03.04.24), the most used commercially-friendly 0-shot classifier.

📄 License

This project is licensed under the MIT license.