| | --- |
| | license: apache-2.0 |
| | --- |
| | |
| | <h1 align="center"> |
| | Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception |
| | </h1> |
| | <p align="center"> |
| | <a href="https://arxiv.org/abs/2410.12788"> |
| | <img alt="arXiv Paper" src="https://img.shields.io/badge/arXiv-Paper-b31b1b.svg?logo=arxiv"> |
| | </a> |
| | <a href="https://huggingface.co/papers/2410.12788"> |
| | <img src="https://img.shields.io/badge/Huggingface-Paper-yellow?style=flat-square&logo=huggingface"> |
| | </a> |
| | <a href="https://opensource.org/license/apache-2-0"> |
| | <img alt="Apache 2.0 License" src="https://img.shields.io/badge/License-Apache_2.0-green.svg?logo=apache"> |
| | </a> |
| | </p> |
| | |
| | The summary and rewrite models were fully fine-tuned on the Qwen2.5-3B-Instruct utilizing 20K data entries from the CRUD benchmark, which was prepared with ERNIE-3.5-128K and QwQ-32B. |
| |
|
