roberta-base-zeroshot-v2.0-c

Model overview

roberta-base-zeroshot-v2.0-c is published by MoritzLaurer as a RoBERTa zero-shot-classification model. The captured configuration identifies RobertaForSequenceClassification and Safetensors metadata reports 124,647,170 parameters. According to the model card, it belongs to the zeroshot-v2.0 series, and the -c suffix marks training on fully commercially-friendly data. Card data records mit.

Recorded capabilities

Use cases in the source record

• Zero-shot text classification without training data through the Hugging Face pipeline and NLI task format.
• Classification work under strict commercial data requirements using the publisher's recommended -c variant.
• Production inference setups using the documented TEI container and flash-attention compatibility.

Limitations and unknowns

• The model card reports zero-shot and few-shot score tables without extracted per-dataset attribution to this exact -c model, so comparative performance should be read from the source before use.
• No context-window value was extracted from this record.
• Provider state is historical snapshot data and should be refreshed before being presented as current.

Source and provenance

Source: MoritzLaurer/roberta-base-zeroshot-v2.0-c

Captured: Unknown. Processed: 2026-09-07T19:34:34.379990+00:00.

Model description: roberta-base-zeroshot-v2.0-c 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…