Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and te…

Automatic library-wide shuffle for mpd.

Pförtner - the digital door label

Converts simple LaTeX to an unicode approximation (going beyond unicodeit)

Compare two version of an arXiv preprint with a single command.

Run Anything

[CVPR'25] Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System

Unofficial Steam AppImage built using Runimage.

This repository is the official GitHub page of MLBCAP, the first-place winner of the 2nd SciCap Challenge. MLBCAP has been accepted for presentation at AI4Research @AAAI 2025.

m3u playlists for radio music, sorted by popularity

Gruvbox Plus icon pack for Linux desktops based on Gruvbox color theme.

CoLing 2020 Paper Vec2Sent: Probing Sentence Embeddings with Natural Language Generation

Inference script for Oasis 500M

A better Python REPL

Math OCR model that outputs LaTeX and markdown

Convert PDF to markdown + JSON quickly with high accuracy

Interactively explore unstructured datasets from your dataframe.

A general fine-tuning kit geared toward diffusion models.

String-to-String Algorithms for Natural Language Processing

Implementation of Nougat Neural Optical Understanding for Academic Documents

Markdown rendering + Latex extras (equations, tables, ...), with conversion features, for the scientific community

Translation Dataset with Terminology for Kpop Fandom

C++ Library Manager for Windows, Linux, and MacOS

Foundational model for human-like, expressive TTS