sciblox - Easier Data Science and Machine Learning

Material for gpu-mode lectures

LLM inference in C/C++

Tool for generating high quality Synthetic datasets

Sometimes we want to ”reverse” a Markov Chain process. Taking the inverse of the transition matrix allows this to work, but the inverse result is not a transition matrix. If I wanted to model a population going to work, and then going back home, negative and greater than 1 probabilities in the inverse matrix will cause issues. I propose a method to compute the ”inverse” of a transition matrix, and the result is still a transition matrix

Inference, Fine Tuning and many more recipes with Gemma family of models

We developed a data mining solution to scrape data from multiple sources to get the latest and greatest information about health grants. AND - we designed a cool Jupyter Notebook Solution to visualise our 2nd challenge- to get data constantly from a source, and show it in Plotly

Data Science Society of UNSW Lecture Series

Created a Machine Learning system to predict if someone is going to suicide, and proposed some mechanisms to counter and help potential victims.

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

A high-throughput and memory-efficient inference and serving engine for LLMs

Clean, accessible reproduction of DeepSeek R1-Zero

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

A collection of machine learning notes

No repository description provided.

We used NSW Air Quality data, health data, transport OPAL congestion data and also some novel disease spreading algorithms to try model and find correlations between Air Quality, Congestion and Influenza rates.

I noticed that traditional methods to predict a disease outbreak was by performing sentiment analysis on Twitter posts and Google Search terms. Unfortunately, these methods were inadequate, as Twitter and Google is not popular in all countries. So, I created a system to model and predict outbreaks without the need for social media. The system was able to update the probabilities of a virus from spreading from A to B in real time, and I plan to release it to the public next year. I also used Machine Learning and Deep Learning to predict larger long-term virus trends with Google Trends, and this acted as a validator for the MSIRD model.

RAPIDS Sample Notebooks

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

The official PyTorch implementation of Google's Gemma models

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

cuML - RAPIDS Machine Learning Library

efficient arrays of booleans for Python

No repository description provided.

No repository description provided.

We created a new Health Rating system that aggregated data from QANTAS, ABS, Victoria Health and supermarket data to reveal correlations between them. We got Special Commendations for our great work!

No repository description provided.

No repository description provided.

Utils for Unsloth https://github.com/unslothai/unsloth

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

Llama 2 Everywhere (L2E)

Finetuning LLaMA with cleaned datasets

Project Aeros aims to optimise data science processes in Python, and provides the user with easy to use functions and APIs

We're creating a full Earth simulation to predict the future of everything and make JARVIS a reality!

No repository description provided.

GPU Accelerated t-SNE for CUDA with Python bindings

NumPy-like API accelerated with CUDA

Fast, flexible and easy to use probabilistic modelling in Python.

Sphinx theme for readthedocs.org

No repository description provided.

Train transformer language models with reinforcement learning.

An interface library for RL post training with environments.

Public repo for HF blog posts

No repository description provided.

Efficient Triton Kernels for LLM Training

No repository description provided.

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Convert HTML to Markdown

Statsmodels: statistical modeling and econometrics in Python

No repository description provided.

BLAS-like Library Instantiation Software Framework

250+ Fine-tuning & RL Notebooks for text, vision, audio, embedding, TTS models.

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

Throwaway harness for validating release-desktop job graph changes

Throwaway staging: validate CUDA 13.3 prebuilt build leg