Bge M3 Zeroshot V2.0 C

🚀 bge-m3-zeroshot-v2.0-c

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

🚀 Quick Start

The bge-m3-zeroshot-v2.0-c model is part of the zeroshot-v2.0 series, which is specifically designed for efficient zero-shot classification using the Hugging Face pipeline. It can perform classification tasks without the need for training data and can run on both GPUs and CPUs.

✨ Features

Zero-shot Classification

The models in this series can perform classification without training data, leveraging the Natural Language Inference (NLI) task format. Any classification task can be reformulated into the task of determining whether a hypothesis is "true" or "not true" given a text.

Commercial-friendly Data

Some models, including those with a "-c" in the name, are trained on fully commercially-friendly data, making them suitable for users with strict license requirements.

📚 Documentation

Model description

zeroshot-v2.0 series of models

Models in this series are designed for efficient zeroshot classification with the Hugging Face pipeline. These models can do classification without training data and run on both GPUs and CPUs. An overview of the latest zeroshot classifiers is available in my 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 do 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. I first created a list of 500+ diverse text classification tasks for 25 professions in conversations with Mistral-large. The data was manually curated. I then used this as seed data to generate several hundred thousand texts for these tasks 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. Data curation was done in multiple iterations and will be improved in future iterations.
2. Two commercially-friendly NLI datasets: (MNLI, FEVER-NLI). These datasets were added to increase generalization.
3. 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.

💻 Usage Examples

Basic Usage

#!pip install transformers[sentencepiece]
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)

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

🔧 Technical Details

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 model is released under the MIT license.