Pinned Loading

1. uparxive uparxive Public

   llm-friendly dataest for the whole arxiv .tex source.

   Jupyter Notebook 2

2. Seq2SeqAutoregressiveModel Seq2SeqAutoregressiveModel Public

   High order manipulation for Seq2SeqAutoregressiveModel in large size Model and Data.

   Python 2 1

3. Lougat Lougat Public

   Nougat + SAM + Llama -> Lougat ( And more, flougat, slougat, ..... )

   Jupyter Notebook 1

4. sci-bert-finetune sci-bert-finetune Public

   Fineturn your embedding model for science paper

   Python

5. Synthetic-Science Synthetic-Science Public

   Those script try to create Synthetic Science QA answer-question pair efficiently and reasoning

   Python

6. PDF-Extract-Kit-Boost- PDF-Extract-Kit-Boost- Public

   Forked from opendatalab/PDF-Extract-Kit

   A Comprehensive Toolkit for High-Quality PDF Content Extraction

   Python