Matthew McAteer's repositories
Keras_pruning
A walkthrough of how to prune keras models, using both weight-pruning and unit/neuron-pruning.
practicing_trustworthy_machine_learning
GitHub Repo associated with the O'Reilly book "Practicing Trustworthy Machine Learning"
loss_landscapes_tf-keras
Tensorflow/Keras-compatible implementation of https://github.com/tomgoldstein/loss-landscape
rescuerepo
Project for the Bio X AI Hackathon. All about resurrecting old abandonware repos, and reducing the effort to get them up and running again.
automata-experiments
Experiments with Neural Automata
adversarial_losses
Loss landscapes for adversarial training
oodles-of-oods
Taxonomy of out-of-distrubuton errors
awslimitchecker
A script and python package to check your AWS service limits and usage via boto3.
CBF-MassChallenge-Hackathon-2017
Files for hackathon component of Cognitive Builder Faire at MassChallenge
fractal-pretraining
Fork of the Official PyTorch code for the paper "Improving Fractal Pre-training"
Ginger_tri
Transfer learning experiments on novel dataset of rhizome images 🖼️ 🍠(taken in the produce aisle at a Whole Foods grocery store 🛒)
jupyter-text2code
A proof-of-concept jupyter extension which converts english queries into relevant python code
KerasCustomUtilities
Temporary Keras Utility Scripts
noise-weight-theft
Code repository for the paper "Model weight theft with just noise inputs: The curious case of the petulant attacker"
worker-runpod-tgi
Tests for improving quantized LLM speedup using TGI (among other technologies)
ffmpeg-python
Python bindings for FFmpeg - with complex filtering support
LLaMahack_submission
Submission to LLaMahack
NeuS2
Fork of the official code for NeuS2 (forked for build improvements)
Scripts
Fork of sahrendt0's "Personal Script Library" - These scripts are subject to change and breakage, early and often.
SDfu
Stable Diffusers for studies
vllm-gptq
A high-throughput and memory-efficient inference and serving engine for LLMs
wattpricer-widget-demos
Scripts demonstrating visualizations created using data downloaded from the Wattpricer API
worker-runpod-flexgen
Tests for improving quantized LLM speedup using vLLM (among other technologies)
worker-runpod-medusa
Tests for improving quantized LLM speedup using Medusa (among other technologies)