Popular repositories Loading

1. MD-chunker MD-chunker Public

   a powerful Markdown chunking tool that understands document structure. Unlike naive token splitters, it protects atomic elements (code, math, tables), merges by semantic affinity, and scores chunk …

   JavaScript 5 1

2. chemical_dataset chemical_dataset Public

   Jupyter Notebook 3

3. easy-dataset easy-dataset Public

   Forked from ConardLi/easy-dataset

   A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

   JavaScript 3

4. crop_tool crop_tool Public

   For freely cropping and correcting images in batches, especially suitable for image editing with unfixed camera positions, where each image requires a unique designated cropping region.

   Python 3 1

5. surroge_model surroge_model Public

   aspen数据驱动

   Python