Sat-3l-sm is a 3-layer transformer model hosted on Hugging Face for token classification. It forms part of the Segment Any Text project and delivers sentence segmentation for use in text processing pipelines.
The model supports 85 languages and carries an MIT license. It uses the xlm-token architecture and appears under the token-classification task tag. Model weights are provided in Safetensors format with a size of 0.2 billion parameters in F32 tensor type.
Integration occurs through the Transformers library. Code examples show loading via a pipeline for token-classification or directly with AutoModelForTokenClassification using an automatic device map. The repository also lists ONNX export support and provides inference options through notebooks on Google Colab and Kaggle.
Downloads reached 508219 in the most recent month. An arXiv paper at 2406.16678 supplies further technical details on its sentence segmentation approach. The model is distributed as open source under the Segment Any Text organization account.
Sat 3l Sm is an Other AI product. Accurately segmenting text into sentences for multiple languages using a compact transformer model. Sat 3l Sm is an open-source project aimed at developers. The project is open source (MIT). The product ships for the web and API.
Behind Sat 3l Sm is segment-any-text, and the product first shipped in 2020. The project is developed in the open on GitHub with 1.3k stars. Among its 3 catalogued features are Sentence Segmentation, Token Classification, and Multilingual Support. It exposes integrations via a public API.
Latest indexed changes and source events
segment-any-text/sat-3l-sm verified by the PulseGate indexer
Other apps tracked under the same category.
