A DeBERTa-v3-base model fine-tuned for zero-shot classification by framing the task as textual entailment. It allows users to classify text using any set of labels at inference time without retraining. The model is available on Hugging Face and works with standard Transformers pipelines.
In the Other AI space, Deberta V3 Base Zeroshot takes a focused approach. It focuses on classifying text into arbitrary categories without task-specific labeled training data using natural language hypotheses. Deberta V3 Base Zeroshot is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the web, the command line, and API.
Moritz Laurer builds and maintains Deberta V3 Base Zeroshot, and it first shipped in 2023. The project is developed in the open on GitHub with 140 stars. Among its 3 catalogued features are Zero-Shot Classification, Natural Language Inference, and Multi-label Classification.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do