ModernBERT-large is a BERT-based language model hosted on Hugging Face. It is designed for fill-mask tasks and supports long-context processing in English. The model carries the Apache 2.0 license and is published by Answer.AI under the identifier answerdotai/ModernBERT-large.
It belongs to the class of masked language models within the Transformers framework. The model is provided in PyTorch, ONNX, and Safetensors formats. Its parameter count stands at 395881664 in F32 precision, with a total file size of 1583544840 bytes when stored in Safetensors. The associated paper is listed under arXiv 2412.13663.
The model is available for use through the Hugging Face ecosystem, including libraries such as Transformers. It can be deployed via inference providers and supports local applications and notebooks. Community discussions around the model total 15, with both open and closed threads.
ModernBERT-large is intended for developers and researchers working on natural language processing applications that require masked token prediction or extended context handling.
In the Foundation models & chat space, ModernBERT Large takes a focused approach. It focuses on providing advanced fill-mask and long-context NLP capabilities for developers and researchers. It is built as an open-source project for NLP developers and researchers. ModernBERT Large is open source under the Open Source license. The product ships for the web, the command line, and API.
Behind ModernBERT Large is Answer.AI, and the product first shipped in 2024. Key capabilities include fill-mask prediction, long-context support, and transformer architecture.
Latest indexed changes and source events
answerdotai/ModernBERT-large verified by the PulseGate indexer
