BenjaminBossan

ogd

FTRL proximal algorithm according to McMahan et al. 2013

tinytune

Tiny neural network fine-tuning library

pytest-guide

Pytest guide for unittest users

peft

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

corona

pantangle

Extract the source code from your markup document

accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

presentations

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

versiondispatch

Dispatch functions based on the version of installed packages

aidoodle

testing out AIs in games

citytetris

Tetris with a twist

api-inference-community

BenjaminBossan

My short profile

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

doom

dstoolbox

Tools that make working with scikit-learn and pandas easier.

emacs-config

.emacs.d

emacs-config2

My (improved) Emacs config

gemma

Open weights LLM from Google DeepMind.

inferno

Lasagne

Lightweight library to build and train neural networks in Theano

mops

Testing GitHub Workflow

playground

random stuff

public-presentations

Contains public presentations

scikit-learn

scikit-learn: machine learning in Python

skops

skorch-feedstock

A conda-smithy repository for skorch.

Theano

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.