rasbt

deeplearning-models

A collection of various deep learning architectures, models, and tips

LLMs-from-scratch

Implementing a ChatGPT-like LLM from scratch, step by step

python-machine-learning-book

The "Python Machine Learning (1st edition)" book code repository and info resource

mlxtend

A library of extension and helper modules for Python's data analysis and machine learning libraries.

pattern_classification

A collection of tutorials and examples for solving and understanding machine learning and pattern classification tasks

machine-learning-book

Code Repository for Machine Learning with PyTorch and Scikit-Learn

watermark

An IPython magic extension for printing date and time stamps, version numbers, and hardware information

machine-learning-notes

Collection of useful machine learning codes and snippets (originally intended for my personal use)

scipy2023-deeplearning

MachineLearning-QandAI-book

Machine Learning Q and AI book

LLM-finetuning-scripts

dora-from-scratch

LoRA and DoRA from Scratch Implementations

cvpr2023

pytorch-memory-optim

This code repository contains the code used for my "Optimizing Memory Usage for Training LLMs and Vision Transformers in PyTorch" blog post.

nn_plus_gzip

Gzip and nearest neighbors for text classification

RAGs

RAGs: Simple implementations of Retrieval Augmented Generation (RAG) Systems

pycon2024

Tutorial Materials for "The Fundamentals of Modern Deep Learning with PyTorch"

posit2023-python-ml

Workshop materials for posit::conf(2023)

ViT-finetuning-scripts

Vision transformer finetuning scripts

py-args

Python command line tools as productivity supplements for Posix systems

rasbt

pytorch-lightning

Deep learning framework to train, deploy, and ship AI products Lightning fast.

axolotl

Go ahead and axolotl questions

bitsandbytes

8-bit CUDA functions for PyTorch

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, quantization, LoRA fine-tuning, pre-training. Apache 2.0-licensed.

litdata

Streamline data pipelines for AI. Process datasets across 1000s of machines, and optimize data for blazing fast model training.

neurips_llm_efficiency_challenge

NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day

llm-efficiency-challenge.github.io

Website for NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1 GPU + 1 Day

dora

Implementation of DoRA

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.