Llmlingua-2 is a BERT-based model designed for prompt compression and key information extraction from long contexts such as meeting transcripts. It performs token classification to identify important content and is multilingual. The model is available on Hugging Face and can be used with the Transformers library for local or hosted inference.
Llmlingua 2 Bert Base Multilingual Cased Meetingbank is an Other AI product. It focuses on compressing and distilling long meeting transcripts while preserving key information. It is built as an open-source project for developers. Llmlingua 2 Bert Base Multilingual Cased Meetingbank is open source under the Open Source license. It runs on the web and API.
It is developed by Microsoft, and the product first shipped in 2024. Key capabilities include token classification, multilingual support, and meeting transcript optimization.
Latest indexed changes and source events
microsoft/llmlingua-2-bert-base-multilingual-cased-meetingbank verified by the PulseGate indexer
Other apps tracked under the same category.
