This model is a fine-tuned DistilBERT-base-uncased designed for token classification tasks, specifically to detect chunk boundaries in documents. It was created to support better text segmentation for RAG (Retrieval Augmented Generation) systems and other NLP pipelines.
Chonky Distilbert Base Uncased 1 sits in PulseGate's Other AI category. It focuses on identifying chunk boundaries in text to improve retrieval-augmented generation pipelines. It is built as an open-source project for developers. The project is open source (MIT). Chonky Distilbert Base Uncased 1 is available on the web and API.
mirth builds and maintains Chonky Distilbert Base Uncased 1, and it first shipped in 2025. The project is developed in the open on GitHub with 416 stars. Key capabilities include Token Classification, Text Chunking, and RAG Support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match