aflueckiger

followers

following

stars

@textshuttle

Zurich, Switzerland

aflueckiger's starred repositories

fundus

A very simple news crawler with a funny name

Language:PythonMIT13500

NOAH-Corpus

NOAH's Corpus: Part-of-Speech Tagging for Swiss German

NOASSERTION1200

polars

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

Language:RustNOASSERTION2705300

pgvector

Open-source vector similarity search for Postgres

Language:CNOASSERTION999000

surya

OCR, layout analysis, reading order, line detection in 90+ languages

Language:PythonGPL-3.0857900

PyMuPDF-Utilities

Demos, examples and utilities using PyMuPDF

Language:Jupyter NotebookAGPL-3.049800

fastfit

FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes

Language:PythonApache-2.014000

ALMA

State-of-the-art LLM-based translation models.

Language:RubyMIT33500

typer

Typer, build great CLIs. Easy to code. Based on Python type hints.

Language:PythonMIT1463500

lm-hackers

Hackers' Guide to Language Models

Language:Jupyter NotebookApache-2.0173000

LaVague

Large Action Model framework to develop AI Web Agents

Language:PythonApache-2.0472100

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Language:PythonApache-2.01456400

hqq

Official implementation of Half-Quadratic Quantization (HQQ)

Language:PythonApache-2.053400

humanize

Python humanize functions

Language:PythonMIT39400

context-aware-word-vectors

Context aware word vectors

Language:Python400

text-clustering

Easily embed, cluster and semantically label text datasets

Language:PythonApache-2.036700

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Language:PythonApache-2.012739000

flores

The FLORES+ Machine Translation Benchmark

Language:TeXCC-BY-SA-4.06600

wizmap

Explore and interpret large embeddings in your browser with interactive visualization! 📍

Language:TypeScriptMIT37700

latent-scope

A scientific instrument for investigating latent spaces

Language:JavaScriptMIT47900

datamapplot

Creating beautiful plots of data maps

Language:PythonMIT43000

emma

E-commerce MQM Anntoations (Emma)

Language:Jupyter NotebookMIT100

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

Language:PythonMIT556600

emoji

emoji terminal output for Python

Language:PythonNOASSERTION184000

mergekit

Tools for merging pretrained large language models.

Language:PythonLGPL-3.0382800

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Language:PythonBSD-3-Clause526900

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

Language:PythonApache-2.0231000

pyodide

Quarto extension to enable interactive Python code cells in HTML documents using Pyodide

Language:JavaScript4900

pytesseract

A Python wrapper for Google Tesseract

Language:PythonApache-2.0560400

lingua-py

The most accurate natural language detection library for Python, suitable for short text and mixed-language text

Language:PythonApache-2.097000