Beast code in Giters

coder1077's starred repositories

PASTA

PASTA: Post-hoc Attention Steering for LLMs

Language:PythonMIT8700

gpt-paper-title-generator

Generating paper titles (and more!) with GPT trained on data scraped from arXiv.

Language:Jupyter Notebook14200

adaptive-wavelets

Adaptive, interpretable wavelets across domains (NeurIPS 2021)

Language:Jupyter NotebookMIT6900

augmented-interpretable-models

Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.

Language:Jupyter NotebookMIT3700

automated-explanations

Explain a black-box module in natural language.

Language:HTMLMIT3000

iprompt

Finding semantically meaningful and accurate prompts.

Language:Jupyter Notebook4400

tree-prompt

Tree prompting: easy-to-use scikit-learn interface for improved prompting.

Language:Jupyter Notebook2700

imodelsX

Scikit-learn friendly library to interpret, and prompt-engineer text datasets using large language models.

Language:PythonMIT14700

CycleGAN

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Language:LuaNOASSERTION1224000

GAN

Resources and Implementations of Generative Adversarial Nets: GAN, DCGAN, WGAN, CGAN, InfoGAN

Language:Python282700

react-native

A framework for building native applications using React

Language:C++MIT11722800

gan-vae-pretrained-pytorch

Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch.

Language:Jupyter Notebook17200

hierarchical-dnn-interpretations

Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

Language:Jupyter NotebookMIT12400

csinva.github.io

Slides, paper notes, class notes, blog posts, and research on ML 📉, statistics 📊, and AI 🤖.

Language:HTMLMIT54900

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

Language:C++MIT1637800